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

    Neuronpedia

    INDEX
    Explanations

    Federal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mascul
    -0.07
     באותה
    -0.06
    Produ
    -0.06
    حدث
    -0.06
    ส
    -0.06
    /graphql
    -0.06
    Mi
    -0.06
     LOVE
    -0.06
    _PROPERTIES
    -0.06
    lassen
    -0.06
    POSITIVE LOGITS
     tariffs
    0.07
     asteroid
    0.07
     fov
    0.07
     tyr
    0.07
    itä
    0.07
     trunc
    0.07
     Robotics
    0.07
     THROW
    0.07
    Fear
    0.07
     analyzes
    0.07
    Act Density 0.019%

    No Known Activations