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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LinkedIn
    -0.06
    rahim
    -0.06
    iT
    -0.06
     تیم
    -0.06
     SQUARE
    -0.06
    стру
    -0.06
    -week
    -0.06
    dığ
    -0.06
     feminist
    -0.06
     ques
    -0.06
    POSITIVE LOGITS
    .Controller
    0.06
     المل
    0.06
     будут
    0.06
     وت
    0.06
     Compare
    0.06
     یکی
    0.06
    artifact
    0.06
    usic
    0.06
     وج
    0.06
    ahy
    0.06
    Act Density 0.060%

    No Known Activations