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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _components
    -0.08
     latest
    -0.08
     components
    -0.08
    amos
    -0.08
    oted
    -0.08
    lumat
    -0.07
     instructed
    -0.07
     stratégies
    -0.07
     earliest
    -0.07
    resources
    -0.07
    POSITIVE LOGITS
     pleasantly
    0.11
     alsof
    0.10
     angenehm
    0.09
     smoother
    0.09
     angene
    0.09
     agradável
    0.09
     prettig
    0.09
     enjoyable
    0.09
     terasa
    0.09
     soepel
    0.08
    Act Density 0.010%

    No Known Activations