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

    Neuronpedia

    INDEX
    Explanations

    expressions related to mathematical or logical operations

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

    Russian words/phrases

    np_acts-logits-general · gemini-2.0-flash

    how to make or what to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     balls
    -0.61
     Росії
    -0.55
     communism
    -0.51
     madness
    -0.51
     daddy
    -0.49
    льної
    -0.49
     friends
    -0.49
     Sasha
    -0.48
     excepted
    -0.48
    ー
    -0.48
    POSITIVE LOGITS
    ंदीखरीदारी
    0.85
     enfans
    0.81
     plufieurs
    0.77
    expandindo
    0.76
     prisonniers
    0.76
     avoient
    0.75
     épaules
    0.74
     feroit
    0.74
    tagHelperRunner
    0.74
     dieux
    0.73
    Act Density 0.008%

    No Known Activations