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

    Neuronpedia

    INDEX
    Explanations

    area size, scope

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    demand
    -0.08
     собы
    -0.07
     gia
    -0.07
     pornofil
    -0.07
    et
    -0.07
     vak
    -0.07
    验证
    -0.07
    .way
    -0.07
    _DP
    -0.07
    ा।↵↵
    -0.06
    POSITIVE LOGITS
    .VISIBLE
    0.07
    (TRUE
    0.07
     Sit
    0.07
    iciary
    0.06
     apart
    0.06
    nuts
    0.06
    {\"
    0.06
     Secretary
    0.06
     Changes
    0.06
     g
    0.06
    Act Density 0.142%

    No Known Activations