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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (UINT
    -0.07
     grat
    -0.07
     idiot
    -0.07
    .RowCount
    -0.06
     ADDR
    -0.06
     чим
    -0.06
     cytok
    -0.06
    치는
    -0.06
     foolish
    -0.06
     Cyril
    -0.06
    POSITIVE LOGITS
     protections
    0.06
    cle
    0.06
    /w
    0.06
     mins
    0.06
    _us
    0.06
    şt
    0.06
    -million
    0.06
    M
    0.06
    нов
    0.06
    bt
    0.06
    Act Density 0.000%

    No Known Activations