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

    Neuronpedia

    INDEX
    Explanations

    subtype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clans
    -0.07
    adapt
    -0.07
     Levi
    -0.07
    Ta
    -0.06
     Se
    -0.06
    compass
    -0.06
     raj
    -0.06
     comparer
    -0.06
    Hur
    -0.06
    nge
    -0.06
    POSITIVE LOGITS
     كور
    0.07
     жін
    0.06
    يلة
    0.06
    ısız
    0.06
     WOW
    0.06
    ाहक
    0.06
     группы
    0.06
     xúc
    0.06
    _mirror
    0.06
     yerel
    0.06
    Act Density 0.000%

    No Known Activations