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

    Neuronpedia

    INDEX
    Explanations

    Defendants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     religious
    -0.07
    所有
    -0.07
    孝
    -0.06
    job
    -0.06
     call
    -0.06
    ่อย
    -0.06
    .sessions
    -0.06
    徳
    -0.06
    _exam
    -0.06
     рос
    -0.06
    POSITIVE LOGITS
    _verts
    0.08
     ті
    0.07
     č
    0.06
    roduced
    0.06
    -----------
↵
    0.06
     ACPI
    0.06
     Chairs
    0.06
     deneyim
    0.06
    ordon
    0.06
     Commod
    0.06
    Act Density 0.006%

    No Known Activations