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

    Neuronpedia

    INDEX
    Explanations

    references to conflicts or defeats in various contexts

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

    defeated by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.60
    rungsseite
    -0.51
    rawDesc
    -0.50
     CallOverrides
    -0.49
     dAtA
    -0.49
    RefNanny
    -0.48
    borderFill
    -0.48
    niſſe
    -0.47
    AndEndTag
    -0.47
    dafx
    -0.46
    POSITIVE LOGITS
    ierte
    0.38
    Tmp
    0.37
    厚
    0.35
    bulos
    0.34
    key
    0.34
     primed
    0.34
     avoient
    0.33
     key
    0.33
    iasaan
    0.32
     I
    0.32
    Act Density 0.061%

    No Known Activations