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

    Neuronpedia

    INDEX
    Explanations

    figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lust
    -0.07
    sync
    -0.07
     Emerging
    -0.06
    (X
    -0.06
     NZ
    -0.06
    ung
    -0.06
     OB
    -0.06
    od
    -0.06
    (REG
    -0.06
     preview
    -0.06
    POSITIVE LOGITS
     مز
    0.07
    ////////////////////////////////////////////////////////////////////////////////
    0.07
     DISCLAIMED
    0.06
    //===
    0.06
    605
    0.06
    нитель
    0.06
    μέ
    0.06
    -radius
    0.06
     brings
    0.06
    需
    0.06
    Act Density 0.005%

    No Known Activations