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

    Neuronpedia

    INDEX
    Explanations

    Token

    np_max-act · gemini-2.0-flash

    The neuron activates on the numeric PublicKeyToken values (the floating‐point tokens) in the assembly configuration.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .getFont
    -0.07
     bird
    -0.07
    _ok
    -0.06
     rich
    -0.06
    ambio
    -0.06
     rigorous
    -0.06
     nations
    -0.06
     White
    -0.06
     MAL
    -0.06
    world
    -0.06
    POSITIVE LOGITS
    Aggregate
    0.07
    .accel
    0.07
     Společ
    0.07
    -------------</
    0.07
    tvrt
    0.06
    _Add
    0.06
    Charts
    0.06
     zřejmě
    0.06
    ,!
    0.06
    0.06
    Act Density 0.000%

    No Known Activations