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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that denote breaks or pause times (e.g. “lunch,” “break,” “pausa pranzo,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Diff
    -0.08
    -products
    -0.06
    _po
    -0.06
     diarr
    -0.06
    ology
    -0.06
     relative
    -0.06
     territorial
    -0.06
    .hp
    -0.06
    _stderr
    -0.06
    _share
    -0.06
    POSITIVE LOGITS
    ')))↵
    0.07
    glfw
    0.06
     TIMER
    0.06
     ninete
    0.06
     ¡
    0.06
    ']])↵
    0.06
     포
    0.06
     kennen
    0.06
    Brun
    0.06
     Plugin
    0.06
    Act Density 0.010%

    No Known Activations