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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive and does not reliably respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     reprodu
    -0.06
    ubu
    -0.06
    viewModel
    -0.06
     Catholic
    -0.06
     grandfather
    -0.06
    ikit
    -0.06
    _binary
    -0.06
     WORD
    -0.06
     amphib
    -0.06
     Bust
    -0.06
    POSITIVE LOGITS
     Unsupported
    0.07
    (())↵
    0.06
    _MSB
    0.06
    awi
    0.06
     heb
    0.06
    dro
    0.06
    ″E
    0.06
     GF
    0.06
     صالح
    0.06
     محمود
    0.06
    Act Density 0.093%

    No Known Activations