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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    宜昌
    -0.08
    苯
    -0.08
     Sta
    -0.08
    滢
    -0.07
     PT
    -0.07
     VIR
    -0.07
    Dept
    -0.07
    茔
    -0.07
    FileName
    -0.07
    .databind
    -0.07
    POSITIVE LOGITS
    让它
    0.08
     hookers
    0.07
    (program
    0.07
    时代
    0.07
    כמו
    0.07
     sanity
    0.07
    (match
    0.07
    𫖳
    0.07
    .trace
    0.07
    .pointer
    0.07
    Act Density 0.001%

    No Known Activations