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

    Neuronpedia

    INDEX
    Explanations

    react imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wagner
    0.66
     wel
    0.65
     MI
    0.64
     Tan
    0.62
     Aqu
    0.61
     Rol
    0.60
     Drag
    0.60
     tan
    0.59
     Matrix
    0.59
     Kle
    0.58
    POSITIVE LOGITS
    Ба
    0.72
    С
    0.72
    Во
    0.71
    З
    0.70
    П
    0.69
    Г
    0.69
    ह
    0.67
    О
    0.67
    У
    0.66
    По
    0.65
    Act Density 0.000%

    No Known Activations