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

    Neuronpedia

    INDEX
    Explanations

    substit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wines
    -0.07
    Showing
    -0.07
    ぬ
    -0.07
    movies
    -0.07
     learns
    -0.07
    moment
    -0.07
     mingle
    -0.07
     Audio
    -0.06
     communal
    -0.06
    ropa
    -0.06
    POSITIVE LOGITS
    gli
    0.06
     спросил
    0.06
    Additionally
    0.06
     anybody
    0.06
    _SYMBOL
    0.06
    699
    0.06
     SKIP
    0.06
     Vij
    0.06
    894
    0.06
    executable
    0.06
    Act Density 0.004%

    No Known Activations