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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     https
    -0.07
    astr
    -0.06
     Jenny
    -0.06
     pard
    -0.06
     Laure
    -0.06
     LIABILITY
    -0.06
     Thor
    -0.06
    核心
    -0.06
    (paren
    -0.06
     Pr
    -0.06
    POSITIVE LOGITS
    load
    0.07
     Serg
    0.06
     upstream
    0.06
     dose
    0.06
    різ
    0.06
     unleash
    0.06
     outlier
    0.06
     experimentation
    0.06
     heatmap
    0.06
     Matcher
    0.06
    Act Density 0.007%

    No Known Activations