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

    Neuronpedia

    INDEX
    Explanations

    Beginning of media titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TEXT
    0.75
    Global
    0.75
    PRIMARY
    0.69
     Global
    0.67
    Internet
    0.64
    npm
    0.63
    Prim
    0.63
    Text
    0.63
    GitHub
    0.62
    GLOBAL
    0.62
    POSITIVE LOGITS
     était
    0.90
     assassins
    0.87
     temporada
    0.84
     biopic
    0.81
     película
    0.80
     saison
    0.80
     seizoen
    0.79
    谍
    0.79
     rendez
    0.78
     étaient
    0.78
    Act Density 0.112%

    No Known Activations