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

    Neuronpedia

    INDEX
    Explanations

    Episode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relativ
    -0.07
    ailing
    -0.07
    (types
    -0.07
     contaminants
    -0.07
     Practices
    -0.07
     servicios
    -0.07
    [model
    -0.06
     Structures
    -0.06
     process
    -0.06
     dazu
    -0.06
    POSITIVE LOGITS
     episodes
    0.16
     Episode
    0.16
    Episode
    0.15
    isodes
    0.10
     epis
    0.10
     Episodes
    0.09
    episode
    0.09
    isode
    0.08
    odic
    0.08
    _episode
    0.07
    Act Density 0.004%

    No Known Activations