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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وني
    -0.07
     Sky
    -0.07
     необходимости
    -0.06
    анню
    -0.06
     풍
    -0.06
     όμως
    -0.06
    โป
    -0.06
     sk
    -0.06
    _documents
    -0.06
     Düny
    -0.06
    POSITIVE LOGITS
    acích
    0.07
    ιβ
    0.07
     gmail
    0.07
     VOID
    0.06
    entionPolicy
    0.06
     hf
    0.06
    母
    0.06
     fruity
    0.06
     Lesbian
    0.06
     unicode
    0.06
    Act Density 0.021%

    No Known Activations