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

    Neuronpedia

    INDEX
    Explanations

    ds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ds
    -1.15
    DS
    -0.77
     Fire
    -0.74
    ms
    -0.63
    gs
    -0.60
    rs
    -0.56
     Officer
    -0.56
    ed
    -0.55
     ds
    -0.53
    Fire
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.78
     विश्वसनीयता
    0.71
     Italijani
    0.69
     <=",
    0.69
     كومونز
    0.67
     Monsanto
    0.65
     CreateTagHelper
    0.65
    +#+#
    0.65
     nakalista
    0.64
     plástica
    0.63
    Act Density 0.458%

    No Known Activations