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

    Neuronpedia

    INDEX
    Explanations

    nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >X
    -0.07
     şu
    -0.06
    -0.06
    umas
    -0.06
     cellspacing
    -0.06
    Password
    -0.06
     انگلیسی
    -0.06
    -0.06
     Lyn
    -0.06
    建設
    -0.06
    POSITIVE LOGITS
     Орг
    0.08
     대표
    0.07
     ripple
    0.07
     Brooke
    0.07
     legion
    0.07
     Prest
    0.07
     ordin
    0.06
     stood
    0.06
     gast
    0.06
    (sig
    0.06
    Act Density 0.096%

    No Known Activations