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

    Neuronpedia

    INDEX
    Explanations

    research and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.36
    ين
    0.36
     are
    0.34
    ă
    0.33
    ę
    0.33
    ING
    0.31
    स
    0.30
    ة
    0.30
    ec
    0.29
     foc
    0.29
    POSITIVE LOGITS
    tcpHeader
    0.33
    uterine
    0.33
     Exodus
    0.30
     Aspergillus
    0.30
     ACh
    0.30
     Α
    0.29
    匼
    0.29
     Antennes
    0.29
     Thương
    0.29
    ㄼ
    0.29
    Act Density 0.021%

    No Known Activations