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
    The
    -0.82
    ,
    -0.61
    campal
    -0.49
    making
    -0.48
    FOC
    -0.46
    Making
    -0.45
    keypress
    -0.44
     hidrat
    -0.44
    resar
    -0.44
     making
    -0.44
    POSITIVE LOGITS
    Autoritní
    0.72
    matically
    0.64
    MigrationBuilder
    0.60
    cemment
    0.59
     Confira
    0.57
     undersigned
    0.54
    saurus
    0.54
    você
    0.54
     funniest
    0.54
     Вікі
    0.53
    Act Density 0.257%

    No Known Activations