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

    Neuronpedia

    INDEX
    Explanations

    overview

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sentence
    -0.07
     Tue
    -0.07
    ucle
    -0.07
    Thread
    -0.07
    ์ต
    -0.07
     Dust
    -0.07
    Sentence
    -0.07
     inflicted
    -0.07
     sin
    -0.07
     dítě
    -0.07
    POSITIVE LOGITS
     overview
    0.13
     Overview
    0.09
    overview
    0.08
    Roz
    0.07
    รว
    0.07
    -over
    0.07
    _over
    0.07
    orian
    0.07
     Roz
    0.06
     overhaul
    0.06
    Act Density 0.008%

    No Known Activations