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

    Neuronpedia

    INDEX
    Explanations

    uk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,num
    -0.07
    多重
    -0.06
     bored
    -0.06
     Please
    -0.06
    :])↵
    -0.06
     iterative
    -0.06
    ization
    -0.06
     term
    -0.06
    轷
    -0.06
    (regex
    -0.06
    POSITIVE LOGITS
     natuur
    0.07
    Ⲕ
    0.07
    .visual
    0.07
    civil
    0.07
     Cake
    0.07
    licken
    0.06
     acquaintance
    0.06
    _FRIEND
    0.06
     activating
    0.06
    właści
    0.06
    Act Density 0.002%

    No Known Activations