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

    Neuronpedia

    INDEX
    Explanations

    descriptive writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     편
    -0.08
    れ
    -0.07
     док
    -0.06
     переп
    -0.06
     ن
    -0.06
    ypse
    -0.06
     partisan
    -0.06
     Romero
    -0.06
    Disconnect
    -0.06
     parti
    -0.06
    POSITIVE LOGITS
     vivid
    0.07
     Attend
    0.07
    Bel
    0.07
    -quality
    0.06
    /><
    0.06
    .init
    0.06
    减
    0.06
    MAR
    0.06
     Thổ
    0.06
     effective
    0.06
    Act Density 0.024%

    No Known Activations