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

    Neuronpedia

    INDEX
    Explanations

    arrest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erf
    -0.07
    Martin
    -0.06
     cancer
    -0.06
    Aff
    -0.06
    iga
    -0.06
     Cancer
    -0.06
     Fil
    -0.06
     Manus
    -0.06
     bullying
    -0.06
     fert
    -0.06
    POSITIVE LOGITS
    opl
    0.07
    осуд
    0.07
     toItem
    0.07
     пункт
    0.07
    ữu
    0.07
    него
    0.06
     experimenting
    0.06
     provoz
    0.06
    -stop
    0.06
     BrowserAnimationsModule
    0.06
    Act Density 0.022%

    No Known Activations