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

    Neuronpedia

    INDEX
    Explanations

    Isolate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     залеж
    -0.07
    ของ
    -0.07
    άνα
    -0.07
    086
    -0.07
     nuevos
    -0.06
     -->↵
    -0.06
    ์ของ
    -0.06
    requency
    -0.06
    	inter
    -0.06
     GCBO
    -0.06
    POSITIVE LOGITS
    save
    0.06
    Tac
    0.06
     headlines
    0.06
    uParam
    0.06
    acting
    0.06
    auto
    0.06
    χε
    0.06
    moth
    0.06
     testimonials
    0.06
     definitions
    0.06
    Act Density 0.011%

    No Known Activations