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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nas
    -0.07
     równ
    -0.07
    esus
    -0.07
     parece
    -0.06
    Em
    -0.06
    onis
    -0.06
    attached
    -0.06
     νο
    -0.06
    ób
    -0.06
     neur
    -0.06
    POSITIVE LOGITS
    _chip
    0.08
     jint
    0.07
     codigo
    0.06
    :";↵
    0.06
     JAN
    0.06
     maintaining
    0.06
     Geoffrey
    0.06
    :',↵
    0.06
     evaluating
    0.06
    .scal
    0.06
    Act Density 0.053%

    No Known Activations