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

    Neuronpedia

    INDEX
    Explanations

    preservation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    游击队
    -0.07
    艅
    -0.07
    鳖
    -0.07
     Österreich
    -0.07
    ril
    -0.07
    Neighbor
    -0.07
    Ť
    -0.06
     bí
    -0.06
     BrowserModule
    -0.06
    蓬勃发展
    -0.06
    POSITIVE LOGITS
    力还是自
    0.08
    ')↵↵
    0.08
     {\
    0.07
    乃至
    0.07
     rehabilit
    0.07
    夹
    0.07
    ")↵
    0.07
     Pall
    0.07
     catal
    0.07
    yles
    0.06
    Act Density 0.078%

    No Known Activations