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

    Neuronpedia

    INDEX
    Explanations

    harmful

    np_max-act · gemini-2.0-flash

    This neuron never activates and thus doesn’t detect any specific feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .libs
    -0.08
    _taken
    -0.07
    -less
    -0.07
     수
    -0.06
    -background
    -0.06
     Intl
    -0.06
     ответ
    -0.06
     offering
    -0.06
    �
    -0.06
     strftime
    -0.06
    POSITIVE LOGITS
     Sergeant
    0.07
    phe
    0.07
     नए
    0.06
    !!↵↵
    0.06
    澳
    0.06
    fuel
    0.06
     vinc
    0.06
    ROME
    0.06
     Oliv
    0.06
    Leader
    0.06
    Act Density 0.045%

    No Known Activations