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

    Neuronpedia

    INDEX
    Explanations

    code assignment parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sche
    0.46
    guessing
    0.44
     Sche
    0.43
    क्षात्कार
    0.43
    ecta
    0.42
    your
    0.42
    ecs
    0.42
    cartes
    0.41
    will
    0.41
    aa
    0.41
    POSITIVE LOGITS
     crush
    0.41
    XMLHttpRequest
    0.41
     напо
    0.40
    ృతి
    0.39
    ろしく
    0.38
     forested
    0.38
    ControlButton
    0.37
     sustain
    0.37
     {%
    0.36
    Forest
    0.35
    Act Density 0.000%

    No Known Activations