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

    Neuronpedia

    INDEX
    Explanations

    canvas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =o
    -0.08
     словами
    -0.07
    ователь
    -0.07
     milli
    -0.06
     قرن
    -0.06
     Baghd
    -0.06
    (sb
    -0.06
    Filtered
    -0.06
    -mediated
    -0.06
    立て
    -0.06
    POSITIVE LOGITS
    训
    0.07
     ؟
    0.07
    996
    0.07
     أحمد
    0.06
     prat
    0.06
    ..↵
    0.06
     passenger
    0.06
     Penal
    0.06
     ensemble
    0.06
    abus
    0.06
    Act Density 0.001%

    No Known Activations