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
     remin
    -0.07
    432
    -0.07
     продолж
    -0.07
     اخلاق
    -0.06
    PEND
    -0.06
    standing
    -0.06
     milestone
    -0.06
    кид
    -0.06
    templ
    -0.06
    Pref
    -0.06
    POSITIVE LOGITS
     Proj
    0.07
     університет
    0.06
    ری
    0.06
    _DI
    0.06
    /auth
    0.06
    .MSG
    0.06
    ato
    0.06
    USAGE
    0.06
    .obs
    0.06
    DBC
    0.06
    Act Density 0.000%

    No Known Activations