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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals (especially decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     whiskey
    -0.07
     подв
    -0.07
     OCC
    -0.06
    .keys
    -0.06
     lizard
    -0.06
    mind
    -0.06
    pedido
    -0.06
     pockets
    -0.06
    ázky
    -0.06
    fh
    -0.06
    POSITIVE LOGITS
    acje
    0.06
     Bhar
    0.06
    Cur
    0.06
     Scalia
    0.06
    PMC
    0.06
     Genetic
    0.06
     bubb
    0.06
    union
    0.06
     publik
    0.06
    boa
    0.06
    Act Density 0.468%

    No Known Activations