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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash

    This neuron fires on words that express logical implication (e.g. “implies”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    র
    -0.07
    Stmt
    -0.07
    	var
    -0.07
     strings
    -0.07
    NONE
    -0.06
    _t
    -0.06
    82
    -0.06
     TLC
    -0.06
    ós
    -0.06
    836
    -0.06
    POSITIVE LOGITS
    &ZeroWidthSpace
    0.07
    _IMAGE
    0.06
    "sync
    0.06
     บ
    0.06
    .isUser
    0.06
     promotional
    0.06
    upakan
    0.06
    uibModal
    0.06
     Priest
    0.06
    Collapse
    0.06
    Act Density 0.004%

    No Known Activations