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

    Neuronpedia

    INDEX
    Explanations

    seek

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to seeking or positioning in a stream or file (e.g. “seek,” “lseek,” “Tell,” “pos,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    録
    -0.08
    　　　　　　
    -0.06
     실시
    -0.06
     yıldız
    -0.06
    盒
    -0.06
    .bmp
    -0.06
     substitutes
    -0.06
    _udp
    -0.06
    ultimo
    -0.06
    637
    -0.06
    POSITIVE LOGITS
    Seek
    0.08
     fseek
    0.08
     seek
    0.07
    シー
    0.07
    ges
    0.07
    <Comment
    0.06
     Fuck
    0.06
     moved
    0.06
     forbidden
    0.06
    seek
    0.06
    Act Density 0.002%

    No Known Activations