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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Terror
    -0.08
    องค์
    -0.08
    -ob
    -0.07
     Observation
    -0.07
    Observation
    -0.07
     bedo
    -0.07
    _obs
    -0.07
     cometido
    -0.07
     betrachten
    -0.07
     purs
    -0.07
    POSITIVE LOGITS
     gleichzeitig
    0.10
     zároveň
    0.09
     allowing
    0.08
    不过
    0.08
     still
    0.08
     simultaneously
    0.08
    增加
    0.08
    避免
    0.08
     sill
    0.08
    扩大
    0.08
    Act Density 0.018%

    No Known Activations