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

    Neuronpedia

    INDEX
    Explanations

    code and text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quoise
    -0.06
    idents
    -0.06
     maneu
    -0.06
    umlah
    -0.06
     wakes
    -0.06
    hid
    -0.06
     Piano
    -0.06
    _adj
    -0.06
     spíše
    -0.06
     ваг
    -0.06
    POSITIVE LOGITS
     prac
    0.07
     File
    0.07
    cpf
    0.07
     >=
    0.07
    '<
    0.07
    _NEAR
    0.07
     billeder
    0.07
    .name
    0.06
     courte
    0.06
    .logical
    0.06
    Act Density 0.000%

    No Known Activations