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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &eacute
    -0.07
    	assert
    -0.07
    ุก
    -0.06
    bm
    -0.06
    (Set
    -0.06
     nal
    -0.06
    \Extension
    -0.06
    .iter
    -0.06
    rnek
    -0.06
     sotto
    -0.06
    POSITIVE LOGITS
    happy
    0.07
     дет
    0.07
    verte
    0.06
    Dto
    0.06
    ILLE
    0.06
     dealing
    0.06
     Anime
    0.06
    camera
    0.06
     Prix
    0.06
     borrow
    0.06
    Act Density 0.000%

    No Known Activations