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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artig
    -0.08
     künst
    -0.08
     Mot
    -0.07
     Bool
    -0.07
    chmal
    -0.07
     beep
    -0.07
     требуется
    -0.07
     flagged
    -0.07
     bool
    -0.07
    amia
    -0.07
    POSITIVE LOGITS
    Viewing
    0.09
     эксплуатации
    0.09
     role
    0.08
    Usage
    0.08
     употреб
    0.08
     воздейств
    0.08
    Role
    0.08
     consumption
    0.08
     readership
    0.08
     भूमिका
    0.08
    Act Density 0.011%

    No Known Activations