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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens that look like floating-point confidence scores.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     GUIStyle
    -0.07
     Hag
    -0.06
     їм
    -0.06
    .cpu
    -0.06
     ワ
    -0.06
    ระบบ
    -0.06
    (tp
    -0.06
    generator
    -0.06
     Napoleon
    -0.06
    Choosing
    -0.06
    POSITIVE LOGITS
    !↵↵↵
    0.07
     واج
    0.06
    ある
    0.06
    胜
    0.06
    _conversion
    0.06
    ematic
    0.06
     balanced
    0.06
     dịch
    0.06
    .netbeans
    0.06
    ;',
    0.06
    Act Density 0.014%

    No Known Activations