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

    Neuronpedia

    INDEX
    Explanations

    violence hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ổi
    0.40
    ation
    0.39
    िश
    0.39
    𝖘
    0.39
    iy
    0.38
    shoulder
    0.37
    done
    0.36
    alex
    0.36
    itud
    0.36
     სი
    0.36
    POSITIVE LOGITS
     NV
    0.52
     pike
    0.43
    察
    0.40
     Nev
    0.40
     artes
    0.39
    getinfo
    0.38
    Intro
    0.38
    тах
    0.37
    ந்திரன்
    0.37
    NV
    0.37
    Act Density 0.003%

    No Known Activations