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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ου
    -0.07
     prose
    -0.06
     brackets
    -0.06
     Fun
    -0.06
    Conditional
    -0.06
     Agreement
    -0.06
     coding
    -0.06
    ζη
    -0.06
    Vis
    -0.06
    啪
    -0.06
    POSITIVE LOGITS
     Coordinates
    0.07
     interrog
    0.07
    fighters
    0.07
    جاج
    0.06
     Dương
    0.06
    deposit
    0.06
     fen
    0.06
    نی
    0.06
     gaan
    0.06
    .toJSONString
    0.06
    Act Density 0.026%

    No Known Activations