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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pearl
    -0.07
     услов
    -0.07
    .AddParameter
    -0.07
    계획
    -0.07
    KA
    -0.07
    Describe
    -0.07
     明
    -0.06
     sandals
    -0.06
     pharmacist
    -0.06
    uzzy
    -0.06
    POSITIVE LOGITS
    への
    0.06
     pada
    0.06
     trả
    0.06
     hrom
    0.06
    責
    0.06
    แหน
    0.06
     Style
    0.06
    .async
    0.06
     は
    0.06
     objc
    0.06
    Act Density 0.003%

    No Known Activations