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

    Neuronpedia

    INDEX
    Explanations

    basil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    важа
    -0.07
     bmi
    -0.06
     срок
    -0.06
    .getLong
    -0.06
     Laden
    -0.06
     Volley
    -0.06
    .messages
    -0.06
    forces
    -0.06
     itibar
    -0.06
    Here
    -0.06
    POSITIVE LOGITS
    çı
    0.08
     ';'
    0.07
     sok
    0.07
    šil
    0.06
    Visual
    0.06
     бел
    0.06
    afa
    0.06
     bust
    0.06
    AIL
    0.06
    leground
    0.06
    Act Density 0.002%

    No Known Activations