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

    Neuronpedia

    INDEX
    Explanations

    Not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    246
    -0.06
    persona
    -0.06
    .Never
    -0.06
     ipsum
    -0.06
     suction
    -0.06
     convex
    -0.06
    گه
    -0.06
    .TIME
    -0.06
     yii
    -0.06
    conut
    -0.06
    POSITIVE LOGITS
     감독
    0.07
    щается
    0.07
     mientras
    0.06
    英语
    0.06
    .="
    0.06
     cursed
    0.06
    (commit
    0.06
     pointless
    0.06
    Labels
    0.06
    وت
    0.06
    Act Density 0.001%

    No Known Activations