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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Read
    -0.07
    .Find
    -0.07
    .Byte
    -0.07
     entityId
    -0.06
    ch
    -0.06
    _THREAD
    -0.06
     Nut
    -0.06
     Forum
    -0.06
    COPY
    -0.06
     Penis
    -0.06
    POSITIVE LOGITS
     hãy
    0.08
     say
    0.07
    よ
    0.07
     vowed
    0.06
     biggest
    0.06
     Entre
    0.06
    nom
    0.06
     unpack
    0.06
    身上
    0.06
    エ
    0.06
    Act Density 0.023%

    No Known Activations