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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ////////////////////////////////////////////////////////////////////////////////////////////////
    -0.06
    게임
    -0.06
     код
    -0.06
    .att
    -0.06
     अर
    -0.06
     diğer
    -0.06
    _broadcast
    -0.06
    (red
    -0.06
     '{{
    -0.06
    斯特
    -0.05
    POSITIVE LOGITS
     пох
    0.07
     Auth
    0.06
    elsen
    0.06
     Perm
    0.06
    ::::/
    0.06
    -payment
    0.06
    .xx
    0.06
    -efficient
    0.06
    entity
    0.06
    ılığıyla
    0.06
    Act Density 0.002%

    No Known Activations