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

    Neuronpedia

    INDEX
    Explanations

    model answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     issues
    0.70
     checkboxes
    0.65
     stems
    0.63
     etc
    0.63
     permeate
    0.63
     stem
    0.62
     spent
    0.62
     disposable
    0.61
     dus
    0.61
     categories
    0.61
    POSITIVE LOGITS
    €™
    1.07
    ‚¬
    0.97
    apos
    0.94
    €
    0.93
    ¢
    0.90
    Emily
    0.87
    Thin
    0.87
    Ž
    0.86
    ž
    0.86
    ￢
    0.86
    Act Density 0.088%

    No Known Activations