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

    Neuronpedia

    INDEX
    Explanations

    outdoor environments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medal
    -0.08
    _yield
    -0.07
     renewed
    -0.07
     Gems
    -0.07
    seo
    -0.06
    并不
    -0.06
     slew
    -0.06
    ogenic
    -0.06
    .PathVariable
    -0.06
     Committee
    -0.06
    POSITIVE LOGITS
    (tolua
    0.06
     wrestling
    0.06
    ehen
    0.06
     gating
    0.06
     -->↵↵↵
    0.05
    aveled
    0.05
    '>↵↵
    0.05
     poles
    0.05
    -UA
    0.05
    ุป
    0.05
    Act Density 0.027%

    No Known Activations