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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on standalone numeric answer tokens (in particular “0” and “1”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     circulation
    -0.07
     bekommen
    -0.07
    रत
    -0.07
     bekom
    -0.07
    �ん
    -0.06
     Subject
    -0.06
    qn
    -0.06
    업체
    -0.06
     Maur
    -0.06
    ースト
    -0.06
    POSITIVE LOGITS
     adec
    0.06
     Trip
    0.06
     veces
    0.06
    電子
    0.06
     fertil
    0.06
     inj
    0.06
     struggled
    0.06
    .getInputStream
    0.06
     علاق
    0.06
     lingu
    0.06
    Act Density 0.005%

    No Known Activations