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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SW
    -0.08
     Amy
    -0.07
    ocaly
    -0.07
     Critics
    -0.07
     bottles
    -0.07
     deprecated
    -0.06
    Average
    -0.06
     Giám
    -0.06
    。这
    -0.06
     Naomi
    -0.06
    POSITIVE LOGITS
    γε
    0.06
     anos
    0.06
    _IP
    0.06
    Concat
    0.06
    ленні
    0.06
    idata
    0.06
     αρι
    0.06
    _dual
    0.06
     sip
    0.06
    _dot
    0.06
    Act Density 0.153%

    No Known Activations