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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xu
    -0.07
    panion
    -0.07
     abb
    -0.06
     pn
    -0.06
     horrors
    -0.06
     fibers
    -0.06
     bốn
    -0.06
    %c
    -0.06
     hinges
    -0.06
     Hazard
    -0.06
    POSITIVE LOGITS
    annonce
    0.07
    داد
    0.07
    realloc
    0.07
     nightclub
    0.06
    ;set
    0.06
    ת
    0.06
    (scene
    0.06
    คร
    0.06
    znik
    0.06
    .onreadystatechange
    0.06
    Act Density 0.019%

    No Known Activations