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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Oh
    -0.06
     multiplier
    -0.06
     amore
    -0.06
    いた
    -0.06
     Buffalo
    -0.06
    าของ
    -0.06
    เพลง
    -0.06
     лікування
    -0.06
    alıdır
    -0.06
    ope
    -0.06
    POSITIVE LOGITS
    .onSubmit
    0.07
    成本
    0.07
     ACTIVE
    0.06
     scraps
    0.06
     absent
    0.06
    ellen
    0.06
    _SCREEN
    0.06
    _failed
    0.06
     condition
    0.06
    ursion
    0.06
    Act Density 0.001%

    No Known Activations