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

    Neuronpedia

    INDEX
    Explanations

    Musical scores

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expressly
    -0.07
    ftype
    -0.07
     Putting
    -0.06
     Digital
    -0.06
    _ent
    -0.06
    spark
    -0.06
    -but
    -0.06
     miser
    -0.06
     moż
    -0.06
     faux
    -0.06
    POSITIVE LOGITS
    机关
    0.07
    �
    0.06
     صد
    0.06
    소년
    0.06
     ا
    0.06
     तन
    0.06
     đỡ
    0.06
     bulunduğu
    0.06
    :str
    0.06
    ivable
    0.06
    Act Density 0.008%

    No Known Activations