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

    Neuronpedia

    INDEX
    Explanations

    helpful useful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    appeared
    -0.07
     mastered
    -0.06
    RuntimeObject
    -0.06
     initializing
    -0.06
    Rank
    -0.06
    *)(
    -0.06
    阳城
    -0.06
     Gir
    -0.06
     TER
    -0.06
     Tao
    -0.06
    POSITIVE LOGITS
    有些
    0.06
     густ
    0.06
    都不
    0.06
     Sk
    0.06
     quarter
    0.06
     thiên
    0.06
     Sür
    0.06
    .ComponentModel
    0.06
    ráž
    0.06
     clerk
    0.06
    Act Density 0.013%

    No Known Activations