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

    Neuronpedia

    INDEX
    Explanations

    closest number math questions

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens that include a decimal point (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ///
    -0.06
    George
    -0.06
    刻
    -0.06
    Honda
    -0.06
    KC
    -0.06
     Cue
    -0.06
     |
    -0.06
    xEC
    -0.06
    >c
    -0.06
     ">
    -0.06
    POSITIVE LOGITS
     Scalars
    0.07
    Extern
    0.07
    .batch
    0.07
     времен
    0.07
     planetary
    0.07
    асти
    0.07
    placement
    0.07
    nant
    0.07
    isma
    0.07
    -address
    0.06
    Act Density 0.003%

    No Known Activations