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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron activates on decimal numbers (floating-point numeric tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bunifu
    -0.07
    .bunifu
    -0.07
     TableCell
    -0.07
    }}>
    -0.07
     growth
    -0.06
    ="%
    -0.06
     rejected
    -0.06
    creens
    -0.06
     extinct
    -0.06
     Tyler
    -0.06
    POSITIVE LOGITS
    езультат
    0.08
    ،↵
    0.07
    ..
    0.07
    alach
    0.07
    ,↵↵↵
    0.07
    !↵↵
    0.06
    ，他
    0.06
     MOT
    0.06
     …
    0.06
     modest
    0.06
    Act Density 0.055%

    No Known Activations