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

    Neuronpedia

    INDEX
    Explanations

    solutions to math problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    smoked
    0.44
     defiance
    0.42
     smoked
    0.41
     vectors
    0.40
     sinus
    0.40
    ảng
    0.39
     centred
    0.39
     experiment
    0.38
     smoky
    0.38
     canvas
    0.38
    POSITIVE LOGITS
     втра
    0.49
     obiect
    0.48
     sure
    0.46
    ෂ
    0.45
     теря
    0.45
     remplacer
    0.43
     OBJECT
    0.43
     perdió
    0.41
    的对象
    0.41
     शुर
    0.41
    Act Density 0.003%

    No Known Activations