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

    Neuronpedia

    INDEX
    Explanations

    1900s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    common
    -0.07
    σφ
    -0.06
     Burton
    -0.06
    (ff
    -0.06
     과
    -0.06
    权
    -0.06
    from
    -0.06
     приготов
    -0.06
    до
    -0.06
    讓
    -0.06
    POSITIVE LOGITS
     Stake
    0.08
    _PAGE
    0.07
     passer
    0.07
     torso
    0.06
    _before
    0.06
    への
    0.06
    _hdl
    0.06
     HEAD
    0.06
     ресур
    0.06
    196
    0.06
    Act Density 0.098%

    No Known Activations