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

    Neuronpedia

    INDEX
    Explanations

    factual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fragment
    -0.07
     Victor
    -0.06
    (skill
    -0.06
    ных
    -0.06
     splits
    -0.06
    icide
    -0.06
    .requireNonNull
    -0.06
    าย
    -0.06
    -only
    -0.06
    ียว
    -0.06
    POSITIVE LOGITS
     insanlar
    0.07
    .QLabel
    0.07
     cardboard
    0.07
     --------------------------------
    0.07
     unidentified
    0.06
     kendi
    0.06
    *',
    0.06
     законом
    0.06
    づ
    0.06
    @property
    0.06
    Act Density 0.098%

    No Known Activations