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

    Neuronpedia

    INDEX
    Explanations

    exemplary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -caret
    -0.06
    죽
    -0.06
     cow
    -0.06
     wo
    -0.06
     米
    -0.06
    richText
    -0.06
    .games
    -0.06
    手に
    -0.06
    ocio
    -0.06
    (gt
    -0.06
    POSITIVE LOGITS
    AGING
    0.07
    ;d
    0.07
     discouraged
    0.06
    Phill
    0.06
     karak
    0.06
    Org
    0.06
    Œ
    0.06
    Profiler
    0.06
    sources
    0.06
     قي
    0.06
    Act Density 0.000%

    No Known Activations