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

    Neuronpedia

    INDEX
    Explanations

    stains on surfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     s
    0.73
    the
    0.71
    ال
    0.66
    in
    0.65
    \
    0.63
     the
    0.62
     sandals
    0.62
     success
    0.61
    Create
    0.59
    ;
    0.59
    POSITIVE LOGITS
     MDLVertex
    0.70
     previstas
    0.68
     manchas
    0.66
     የበለጠ
    0.64
     понятия
    0.63
     problème
    0.63
    বাসী
    0.63
     políticos
    0.63
    бычно
    0.62
    нется
    0.61
    Act Density 0.013%

    No Known Activations