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

    Neuronpedia

    INDEX
    Explanations

    say capital letter word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dermed
    -0.08
    isper
    -0.08
    sero
    -0.08
     sanitizer
    -0.08
     dann
    -0.08
     وأن
    -0.08
     تنهن
    -0.08
    तान
    -0.07
     ocho
    -0.07
    luk
    -0.07
    POSITIVE LOGITS
     কিংবা
    0.10
     approach
    0.09
     or
    0.09
     немесе
    0.09
     involves
    0.09
    或者
    0.09
     Approach
    0.09
     یا
    0.09
    _method
    0.09
     revolve
    0.09
    Act Density 0.042%

    No Known Activations