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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurements expressed as decimal values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Instead
    -0.07
     Discounts
    -0.07
     základ
    -0.06
    tones
    -0.06
    ous
    -0.06
    amaño
    -0.06
    延
    -0.06
     aux
    -0.06
     headed
    -0.06
    indx
    -0.06
    POSITIVE LOGITS
     suck
    0.07
    [k
    0.06
    же
    0.06
    .ndim
    0.06
     πρέπει
    0.06
    ftar
    0.06
    �
    0.06
    .Ε
    0.06
     hated
    0.06
    [-
    0.06
    Act Density 0.157%

    No Known Activations