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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hat
    -0.07
     Fits
    -0.06
    OSE
    -0.06
     Pacific
    -0.06
     minced
    -0.06
    apan
    -0.06
     digits
    -0.06
    .scroll
    -0.06
     TMP
    -0.06
     Hin
    -0.06
    POSITIVE LOGITS
     shale
    0.06
     shrine
    0.06
     perman
    0.06
    uania
    0.06
     그녀의
    0.05
     llvm
    0.05
    äge
    0.05
    ثال
    0.05
    Campaign
    0.05
     Sa
    0.05
    Act Density 0.006%

    No Known Activations