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

    Neuronpedia

    INDEX
    Explanations

    programming errors

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the text names or discusses runtime error/exception types (e.g. “InvalidOperationException,” “ExpressionChangedAfterItHasBeenCheckedError,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ToolStripButton
    -0.07
     spline
    -0.06
    398
    -0.06
    添加
    -0.06
    iten
    -0.06
    ández
    -0.06
    light
    -0.06
     семей
    -0.06
    ल
    -0.06
     тепло
    -0.06
    POSITIVE LOGITS
     felse
    0.07
    Near
    0.07
     allow
    0.07
    Fear
    0.07
     QUI
    0.07
     znam
    0.07
     Watch
    0.06
    ob
    0.06
    [selected
    0.06
     watch
    0.06
    Act Density 0.014%

    No Known Activations