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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron responds to words describing orientation or positional states (e.g. inverted, erect, downward, upward).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _socket
    -0.07
    структор
    -0.06
    控制
    -0.06
    Setter
    -0.06
    .Reader
    -0.06
     багать
    -0.06
    -gallery
    -0.06
     लड़क
    -0.06
    .WRITE
    -0.06
    .filters
    -0.06
    POSITIVE LOGITS
     fundraising
    0.06
     Neon
    0.06
     war
    0.06
     snatch
    0.06
    =os
    0.06
    섭
    0.06
     intersect
    0.06
    -vertical
    0.06
    .rstrip
    0.06
     valeur
    0.06
    Act Density 0.101%

    No Known Activations