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

    Neuronpedia

    INDEX
    Explanations

    Ensuring accuracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inaugural
    -0.07
    _social
    -0.07
     запис
    -0.07
    Ke
    -0.06
    _decision
    -0.06
     drama
    -0.06
    官
    -0.06
     governance
    -0.06
     Held
    -0.06
    ndl
    -0.06
    POSITIVE LOGITS
    _PIPE
    0.07
     Đ
    0.07
     sollen
    0.07
     sor
    0.06
    onyms
    0.06
    HQ
    0.06
    oenix
    0.06
    charset
    0.06
    hat
    0.06
    rex
    0.06
    Act Density 0.082%

    No Known Activations