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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    The neuron is detecting code that computes the projection of a point onto a line (and the distance from the point to that line).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pillars
    -0.07
     daycare
    -0.06
    _sys
    -0.06
    icts
    -0.06
    ー�
    -0.06
     toen
    -0.06
    (UI
    -0.06
     土
    -0.06
    카
    -0.06
    _MI
    -0.06
    POSITIVE LOGITS
     Tomas
    0.07
    psilon
    0.06
    ábado
    0.06
    _report
    0.06
    .runtime
    0.06
    HIP
    0.06
    ldkf
    0.06
    NSIndexPath
    0.06
    .EventSystems
    0.06
    )./
    0.06
    Act Density 0.009%

    No Known Activations