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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron remains inactive—it does not detect or respond to any particular tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ellite
    -0.07
    -track
    -0.07
     light
    -0.07
    ateur
    -0.06
    >`;↵
    -0.06
    _ranges
    -0.06
    -u
    -0.06
    _Controller
    -0.06
    '}↵
    -0.06
    389
    -0.06
    POSITIVE LOGITS
     نی
    0.07
    issance
    0.06
     Бол
    0.06
    friends
    0.06
     Disney
    0.06
    uble
    0.06
     dereg
    0.06
     พ
    0.06
    경기
    0.06
     dej
    0.06
    Act Density 0.075%

    No Known Activations