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

    Neuronpedia

    INDEX
    Explanations

    contrasting phrases, followed by specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Claude
    0.41
    蚣
    0.41
    谠
    0.40
    bicycle
    0.39
    ッドレス
    0.39
     Override
    0.38
    દા
    0.38
    드렸
    0.38
    𝘋
    0.38
    morgan
    0.38
    POSITIVE LOGITS
     gamm
    0.46
    \
    0.46
    了
    0.44
    (
    0.44
     stars
    0.43
    /
    0.43
     the
    0.43
     Yunan
    0.42
    0.42
    =
    0.42
    Act Density 0.000%

    No Known Activations