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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    This neuron activates on negation of effects—phrases expressing that something “did not” occur or had “no” effect.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     소
    -0.06
    undles
    -0.06
     Dalton
    -0.06
    uforia
    -0.06
     abyss
    -0.06
     alumnos
    -0.06
    えて
    -0.06
    ثمان
    -0.06
    dbe
    -0.06
    Footer
    -0.06
    POSITIVE LOGITS
    ㅋㅋ
    0.07
    ponge
    0.06
     Turkish
    0.06
    .／
    0.06
     typename
    0.06
    .Decimal
    0.06
     popul
    0.06
    �
    0.06
     breadcrumbs
    0.06
    раниц
    0.06
    Act Density 0.026%

    No Known Activations