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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mpjes
    -0.07
    귱
    -0.07
    .Ultra
    -0.07
    熛
    -0.06
    Such
    -0.06
    的热情
    -0.06
    大赛
    -0.06
    باشر
    -0.06
     בעזר
    -0.06
    ernen
    -0.06
    POSITIVE LOGITS
     ostream
    0.08
    /of
    0.08
    HLT
    0.07
     NE
    0.07
    connections
    0.07
    孱
    0.07
     Would
    0.07
     anatom
    0.06
    _____
    0.06
     agon
    0.06
    Act Density 0.028%

    No Known Activations