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

    Neuronpedia

    INDEX
    Explanations

    negative

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on negative‐sentiment words or phrases—basically markers of harmful or adverse impacts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     удоб
    -0.07
     perfume
    -0.06
     різ
    -0.06
    了解
    -0.06
     Belize
    -0.06
    .LinearLayoutManager
    -0.06
    .dataGridViewTextBoxColumn
    -0.06
     VARIANT
    -0.06
    -free
    -0.06
    _CheckedChanged
    -0.06
    POSITIVE LOGITS
    emonic
    0.07
     numerical
    0.07
     dec
    0.07
                             ↵
    0.07
    __,↵
    0.07
    _plate
    0.07
    eken
    0.06
    ↵
    0.06
    ındaki
    0.06
     rails
    0.06
    Act Density 0.020%

    No Known Activations