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

    Neuronpedia

    INDEX
    Explanations

    past tense

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ISO
    -0.06
     BoxDecoration
    -0.06
    PROCESS
    -0.06
    INGLE
    -0.06
    anghai
    -0.06
    _sock
    -0.06
    icks
    -0.06
    _timing
    -0.06
    _vc
    -0.06
     evac
    -0.06
    POSITIVE LOGITS
    �
    0.07
     "_
    0.07
     konusu
    0.06
     topLevel
    0.06
     �
    0.06
     znamená
    0.06
     Psi
    0.06
     největší
    0.06
     ydk
    0.06
     ********************************
    0.06
    Act Density 0.041%

    No Known Activations