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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    之心
    -0.08
    דווח
    -0.08
    أم
    -0.07
     Ку
    -0.07
    نسخ
    -0.07
    בי
    -0.07
     mundo
    -0.07
    ﰞ
    -0.07
    них
    -0.07
     pequ
    -0.07
    POSITIVE LOGITS
     ){
    0.08
     riv
    0.08
     Criterion
    0.08
    builtin
    0.07
    ",'
    0.07
    '],'
    0.07
     reliability
    0.07
     barg
    0.07
    call
    0.07
    ',)↵
    0.07
    Act Density 0.001%

    No Known Activations