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

    Neuronpedia

    INDEX
    Explanations

    too much

    np_max-act · gemini-2.0-flash

    The neuron responds to adverbial intensifiers signaling excess (e.g. “too deep into expectations”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Validate
    -0.07
    ACCOUNT
    -0.06
    ぇ
    -0.06
    _SERVER
    -0.06
     свою
    -0.06
    INK
    -0.06
     remarked
    -0.06
     Computing
    -0.06
    esto
    -0.06
    .LastName
    -0.06
    POSITIVE LOGITS
    obook
    0.07
    	cat
    0.07
    $PostalCodesNL
    0.06
     джер
    0.06
     Collections
    0.06
    _act
    0.06
     capt
    0.06
     min
    0.06
    .grpc
    0.06
    /rem
    0.06
    Act Density 0.011%

    No Known Activations