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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron does not activate for any tokens (i.e., it detects nothing).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     soaking
    -0.08
    doesn
    -0.07
    Simon
    -0.07
     áp
    -0.07
    Christopher
    -0.07
    /St
    -0.06
    _Com
    -0.06
    pack
    -0.06
     Going
    -0.06
    Pack
    -0.06
    POSITIVE LOGITS
     대한
    0.07
     �
    0.07
     sahibi
    0.07
    (day
    0.06
     ж
    0.06
    đ
    0.06
     більш
    0.06
     دوست
    0.06
    iliar
    0.06
    0.06
    Act Density 0.026%

    No Known Activations