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

    Neuronpedia

    INDEX
    Explanations

    much

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric data, especially floating‐point values and measurement figures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    timestamps
    -0.07
    Ga
    -0.06
     بیرون
    -0.06
    _Instance
    -0.06
    POWER
    -0.06
    ृद
    -0.06
    (filter
    -0.06
    _ref
    -0.06
    .One
    -0.06
    emento
    -0.06
    POSITIVE LOGITS
    .TOP
    0.07
    ocurrency
    0.07
     improving
    0.06
     improve
    0.06
     جنسی
    0.06
    -radio
    0.06
     переп
    0.06
    Makes
    0.06
    auc
    0.06
    uar
    0.06
    Act Density 0.618%

    No Known Activations