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

    Neuronpedia

    INDEX
    Explanations

    iconic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continually
    -0.08
     fullPath
    -0.06
    Ģ
    -0.06
     samo
    -0.06
     roller
    -0.06
     lazy
    -0.06
     comparative
    -0.06
     compute
    -0.06
     schedules
    -0.06
     strengthened
    -0.06
    POSITIVE LOGITS
     iconic
    0.18
    .tc
    0.07
    CppType
    0.07
     ICON
    0.07
    /docs
    0.07
    <Token
    0.06
    typically
    0.06
    lassian
    0.06
    ioc
    0.06
     قتل
    0.06
    Act Density 0.004%

    No Known Activations