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

    Neuronpedia

    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FAILED
    -0.07
    验
    -0.06
    舗
    -0.06
     ArgumentNullException
    -0.06
    践
    -0.06
     наяв
    -0.06
     secondo
    -0.06
     爱
    -0.06
    額
    -0.06
    >|
    -0.06
    POSITIVE LOGITS
     χα
    0.07
     revolves
    0.07
    inclu
    0.06
     Updated
    0.06
     catering
    0.06
    láš
    0.06
     intr
    0.06
     inclu
    0.06
    iliği
    0.06
     Request
    0.06
    Act Density 0.012%

    No Known Activations