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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��이
    -0.07
     flashlight
    -0.07
    colon
    -0.06
     Span
    -0.06
    resar
    -0.06
    ué
    -0.06
     lys
    -0.06
     bru
    -0.06
     Aside
    -0.06
     khuẩn
    -0.06
    POSITIVE LOGITS
    Α
    0.07
    арамет
    0.07
     hodnot
    0.06
     "---
    0.06
    Toggle
    0.06
    Retrieve
    0.06
     Accred
    0.06
     اینتر
    0.06
     opting
    0.06
    集团
    0.06
    Act Density 0.008%

    No Known Activations