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

    Neuronpedia

    INDEX
    Explanations

    puzzles/algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    打扫
    -0.08
     donde
    -0.07
    .lu
    -0.07
    .TextField
    -0.07
    斥
    -0.07
    _section
    -0.07
     evoke
    -0.07
     Opportunities
    -0.06
    Graphic
    -0.06
    gross
    -0.06
    POSITIVE LOGITS
    "A
    0.07
    خش
    0.07
    uye
    0.07
    歆
    0.07
    zza
    0.07
     הודעה
    0.07
    ------------------------------------------------------------------------------------------------
    0.07
     keras
    0.07
     Russians
    0.06
    깬
    0.06
    Act Density 0.006%

    No Known Activations