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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly those associated with notable contributions or leadership roles

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

    jk or JK sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Blau
    -0.46
     Colman
    -0.44
    快
    -0.42
    estris
    -0.42
    INCREF
    -0.41
     Bochum
    -0.41
     саны
    -0.40
    )})
    -0.39
    幕
    -0.39
     fast
    -0.38
    POSITIVE LOGITS
    JK
    2.20
     JK
    2.11
    jk
    2.09
     jk
    1.80
    Jk
    1.42
    jkl
    0.97
    +#+#
    0.79
    ijk
    0.78
    ValueStyle
    0.78
    jka
    0.77
    Act Density 0.009%

    No Known Activations