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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to extensive explanation and thoroughness

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

    in detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.68
     enfans
    -0.67
     étoient
    -0.57
     balcón
    -0.52
    })->
    -0.51
     chrétien
    -0.50
     Constitucional
    -0.50
     navideño
    -0.49
     zimní
    -0.49
     rempliss
    -0.49
    POSITIVE LOGITS
    AtIndexPath
    0.56
     CURIAM
    0.52
    omitempty
    0.52
     whiteColor
    0.50
     estekak
    0.50
    ArgsConstructor
    0.49
    xically
    0.49
    toFloat
    0.48
     strdup
    0.48
    Viitteet
    0.48
    Act Density 0.045%

    No Known Activations