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

    Neuronpedia

    INDEX
    Explanations

    Code and scientific data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foots
    -1.05
     (
    -0.63
     en
    -0.52
     par
    -0.47
     при
    -0.46
     x
    -0.45
     ap
    -0.45
    (
    -0.45
     van
    -0.44
    par
    -0.43
    POSITIVE LOGITS
    PreferredItem
    0.84
     GIPHY
    0.83
    harusnya
    0.83
    Rhestr
    0.79
     étoient
    0.78
     auroit
    0.77
    openConnection
    0.75
     ―――――
    0.73
     myſelf
    0.73
     étoit
    0.72
    Act Density 0.053%

    No Known Activations