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

    Neuronpedia

    INDEX
    Explanations

    removal

    np_max-act · gemini-2.0-flash

    This neuron detects verbs and phrases that describe someone being forcibly removed or expelled (e.g. “kicked out,” “booted off,” “ejected from”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    compound
    -0.07
    Mesh
    -0.06
    (router
    -0.06
    _string
    -0.06
     installation
    -0.06
    edo
    -0.06
    ินทาง
    -0.06
    po
    -0.06
    permalink
    -0.06
    ","\
    -0.06
    POSITIVE LOGITS
     scrim
    0.06
    тра
    0.06
     Elekt
    0.06
    _readable
    0.06
    _own
    0.06
    `).
    0.06
     перек
    0.06
     QColor
    0.06
     UA
    0.06
    _Show
    0.06
    Act Density 0.011%

    No Known Activations