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

    Neuronpedia

    INDEX
    Explanations

    Surfaces

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     по
    -0.07
     Palin
    -0.07
    (Rect
    -0.07
     Ukraine
    -0.07
    По
    -0.07
    评审
    -0.07
    <Movie
    -0.07
     Expedition
    -0.06
     Haw
    -0.06
     enough
    -0.06
    POSITIVE LOGITS
     RESULTS
    0.07
    fr
    0.07
    urgent
    0.07
    "):↵
    0.07
    稳健
    0.06
    始め
    0.06
     המשתמש
    0.06
     lead
    0.06
     vex
    0.06
    提振
    0.06
    Act Density 0.113%

    No Known Activations