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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SPAN
    -0.07
     hit
    -0.07
     Ginny
    -0.07
    ่อม
    -0.07
     lý
    -0.06
    งส
    -0.06
    iens
    -0.06
     تنظیم
    -0.06
    -action
    -0.06
    َه
    -0.06
    POSITIVE LOGITS
     през
    0.07
     температу
    0.06
    _RIGHT
    0.06
    CSS
    0.06
     warriors
    0.06
    φαρ
    0.06
    camel
    0.06
    umont
    0.06
     garden
    0.06
     террит
    0.06
    Act Density 0.037%

    No Known Activations