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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    듄
    -0.08
    (d
    -0.07
     horrible
    -0.07
    rror
    -0.07
    זר
    -0.07
    ߌ
    -0.06
    ῥ
    -0.06
    	strncpy
    -0.06
    'o
    -0.06
    .setValue
    -0.06
    POSITIVE LOGITS
     hemisphere
    0.07
     Chúng
    0.07
     unlocks
    0.07
     Talk
    0.07
    堍
    0.07
    رياض
    0.07
    ownt
    0.07
    𝔰
    0.07
     thumbs
    0.07
    蜉
    0.07
    Act Density 0.008%

    No Known Activations