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

    Neuronpedia

    INDEX
    Explanations

    Size and intensity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    appear
    -0.08
    Entropy
    -0.08
    computer
    -0.07
    configure
    -0.07
    .timezone
    -0.07
    xfd
    -0.07
     Divider
    -0.06
    上げ
    -0.06
    FSIZE
    -0.06
    仕事
    -0.06
    POSITIVE LOGITS
     Indi
    0.06
     tvb
    0.06
    ेब
    0.06
    -msg
    0.06
    ILT
    0.05
     mediation
    0.05
    Natural
    0.05
     Angola
    0.05
    -cancel
    0.05
     τόσο
    0.05
    Act Density 0.165%

    No Known Activations