Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to delusion and self-perception issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Stubbornness, delusion, and unreasonable beliefs

    np_acts-logits-general · gemini-2.0-flash

    unreasonable application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rujuakan
    -0.64
     AnyObject
    -0.60
    ContentAsync
    -0.56
    
    -0.53
     gero
    -0.52
    ParallelGroup
    -0.52
     AssemblyProduct
    -0.50
    MigrationBuilder
    -0.50
     Sech
    -0.50
     gentle
    -0.50
    POSITIVE LOGITS
     delusion
    1.09
     delusional
    1.05
     deluded
    0.96
     delusions
    0.96
     blindness
    0.93
     blind
    0.92
     aveug
    0.91
     believing
    0.90
     blindly
    0.89
     belief
    0.89
    Act Density 0.443%

    No Known Activations