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
    IDAD
    -0.07
     لك
    -0.07
    btc
    -0.06
     factories
    -0.06
    administration
    -0.06
     Id
    -0.06
    ských
    -0.06
    stras
    -0.06
     있다는
    -0.06
     suffers
    -0.06
    POSITIVE LOGITS
     конс
    0.07
    encoder
    0.07
    -character
    0.06
    (strtolower
    0.06
     Vocabulary
    0.06
    >Create
    0.06
    (Console
    0.06
     "'",
    0.06
     شهرد
    0.06
     graphite
    0.06
    Act Density 0.000%

    No Known Activations