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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron flags purposive constructions—phrases marking “in order to” or “so as to” type purpose clauses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Barcelona
    -0.07
    _LEAVE
    -0.06
     Pistol
    -0.06
    .Circle
    -0.06
     outbreaks
    -0.06
    パ
    -0.06
    _four
    -0.06
    ucson
    -0.06
    (dialog
    -0.06
     Сан
    -0.06
    POSITIVE LOGITS
    stable
    0.07
                       ↵
    0.07
    candidates
    0.07
    lin
    0.07
     مفهوم
    0.06
    ادية
    0.06
     навчання
    0.06
     unstable
    0.06
     состояния
    0.06
    medi
    0.06
    Act Density 0.062%

    No Known Activations