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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “fallback” (or “fall back”) mechanisms or options in text or code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _instructions
    -0.08
     Completion
    -0.08
     sorter
    -0.08
     Needle
    -0.07
    .groupby
    -0.07
    idian
    -0.07
    ption
    -0.07
    .AddParameter
    -0.07
     дво
    -0.07
     Surface
    -0.07
    POSITIVE LOGITS
     fallback
    0.10
    fallback
    0.07
     milfs
    0.07
    主义
    0.06
    flatMap
    0.06
    handles
    0.06
    lando
    0.06
    -points
    0.06
     Fallout
    0.06
     식
    0.06
    Act Density 0.005%

    No Known Activations