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

    Neuronpedia

    INDEX
    Explanations

    first occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seguire
    0.55
    /
    0.55
     diversi
    0.54
    );
    0.53
    ):
    0.52
     chronological
    0.51
    ),
    0.50
     sporting
    0.50
    чі
    0.50
    :
    0.49
    POSITIVE LOGITS
    이
    0.68
    Folding
    0.64
    Hö
    0.63
    Selections
    0.60
    Units
    0.59
    MV
    0.58
    Bennett
    0.58
    い
    0.58
    Plots
    0.57
    Impact
    0.57
    Act Density 0.003%

    No Known Activations