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

    Neuronpedia

    INDEX
    Explanations

    hand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    allenges
    -0.07
     편집
    -0.07
     الشم
    -0.07
    .assertFalse
    -0.06
     SCRIPT
    -0.06
    'B
    -0.06
     지나
    -0.06
    .sig
    -0.06
    üçük
    -0.06
     dies
    -0.06
    POSITIVE LOGITS
     xmm
    0.07
    ‌المللی
    0.07
    ga
    0.06
    rego
    0.06
     associated
    0.06
     abide
    0.06
    вид
    0.06
     tus
    0.06
    .Feature
    0.06
     birik
    0.05
    Act Density 0.004%

    No Known Activations