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

    Neuronpedia

    INDEX
    Explanations

    overview

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (eventName
    -0.06
    Sure
    -0.06
    носят
    -0.06
     sentence
    -0.06
    олос
    -0.06
     torture
    -0.06
     Rahman
    -0.06
     místo
    -0.06
     директор
    -0.06
    íte
    -0.06
    POSITIVE LOGITS
     overview
    0.10
    .engine
    0.07
     appDelegate
    0.07
     acknowledgement
    0.07
    uating
    0.07
     GridView
    0.07
    okers
    0.06
     Glob
    0.06
    .addObserver
    0.06
    wide
    0.06
    Act Density 0.006%

    No Known Activations