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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الکترون
    -0.07
    nda
    -0.07
    ｜
    -0.07
    テレビ
    -0.07
    急
    -0.07
    　l
    -0.06
    lığının
    -0.06
     innovate
    -0.06
    lediği
    -0.06
     Ngoài
    -0.06
    POSITIVE LOGITS
     přip
    0.07
     dù
    0.07
     referral
    0.07
    亦
    0.06
     mistake
    0.06
    	FOR
    0.06
     δι
    0.06
    лов
    0.06
     VOID
    0.06
    orient
    0.06
    Act Density 0.009%

    No Known Activations