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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لى
    -0.07
     myfile
    -0.07
     sphere
    -0.06
    _unlock
    -0.06
    oke
    -0.06
     save
    -0.06
     endian
    -0.06
    f
    -0.06
    ftype
    -0.06
    (stat
    -0.06
    POSITIVE LOGITS
     jung
    0.08
    име
    0.07
     Garten
    0.07
    Shoot
    0.06
    stdint
    0.06
    _bloc
    0.06
     이동
    0.06
    ingle
    0.06
    确
    0.06
     knowledgeable
    0.06
    Act Density 0.005%

    No Known Activations