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

    Neuronpedia

    INDEX
    Explanations

    vector direction and dot product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estaciones
    1.52
     vía
    1.32
     monies
    1.19
     Tabelle
    1.19
     eyed
    1.14
     saints
    1.14
     mTOR
    1.13
     hypersurface
    1.12
     камеры
    1.12
    附近的
    1.11
    POSITIVE LOGITS
    an
    1.39
    HAV
    1.21
    bles
    1.20
    plication
    1.18
    a
    1.18
    り
    1.18
    ch
    1.16
    ble
    1.15
    fellow
    1.15
    code
    1.10
    Act Density 0.000%

    No Known Activations