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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .title
    -0.07
    inox
    -0.07
    ww
    -0.06
     traits
    -0.06
     execute
    -0.06
    .cap
    -0.06
    .Subject
    -0.06
     Billion
    -0.06
    AdapterFactory
    -0.06
    Overview
    -0.06
    POSITIVE LOGITS
    .visitMethodInsn
    0.07
    gres
    0.07
     Conservatives
    0.06
     spyOn
    0.06
     closet
    0.06
    ۱۴
    0.06
    ΟΥ
    0.06
    require
    0.06
     стрем
    0.06
    cp
    0.06
    Act Density 0.002%

    No Known Activations