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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лот
    -0.07
    eft
    -0.07
     bam
    -0.06
    沃
    -0.06
     sout
    -0.06
    ripe
    -0.06
    鳁
    -0.06
    🗽
    -0.06
     net
    -0.06
    Den
    -0.06
    POSITIVE LOGITS
    ↫
    0.08
     nouvel
    0.08
    	NdrFc
    0.07
    ────
    0.07
     profiling
    0.07
    TabControl
    0.07
    Williams
    0.07
     צריכ
    0.07
     filmmakers
    0.07
     trailed
    0.07
    Act Density 0.006%

    No Known Activations