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

    Neuronpedia

    INDEX
    Explanations

    bit

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “bit,” especially when used as a modifier (e.g., “a little bit”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "]}
    -0.07
     Lund
    -0.07
    .page
    -0.06
    708
    -0.06
     adolescence
    -0.06
    으나
    -0.06
    =~
    -0.06
     Tall
    -0.06
    acji
    -0.06
     NoSuchElementException
    -0.06
    POSITIVE LOGITS
    MORE
    0.07
     nost
    0.07
     Francesco
    0.07
     inconsist
    0.06
     disreg
    0.06
     bit
    0.06
     FT
    0.06
    .Cor
    0.06
     Έ
    0.06
    'in
    0.06
    Act Density 0.005%

    No Known Activations