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

    Neuronpedia

    INDEX
    Explanations

    same directory, software, or project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itinéraires
    0.49
    ’)
    0.47
    да
    0.47
    ’।
    0.46
    䀨
    0.46
    تى
    0.45
    )’
    0.44
    פים
    0.43
     sự
    0.42
    ’;
    0.41
    POSITIVE LOGITS
    0.66
    zelfde
    0.48
     bake
    0.46
     grease
    0.46
     cam
    0.46
     wax
    0.46
    CL
    0.45
     ca
    0.44
    es
    0.44
     plaque
    0.43
    Act Density 0.003%

    No Known Activations