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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ायत
    -0.08
     reluctance
    -0.07
     маль
    -0.07
    　　 　
    -0.07
     grooming
    -0.07
     Buddhist
    -0.06
     residential
    -0.06
     matures
    -0.06
     　
    -0.06
    -placement
    -0.06
    POSITIVE LOGITS
     projecting
    0.06
    gfx
    0.06
    ایی
    0.06
    �
    0.06
    íně
    0.05
    ,</
    0.05
     booklet
    0.05
     Direction
    0.05
    �
    0.05
    Opts
    0.05
    Act Density 0.010%

    No Known Activations