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

    Neuronpedia

    INDEX
    Explanations

    code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trips
    -0.07
    -open
    -0.07
    mix
    -0.06
    figure
    -0.06
     whom
    -0.06
     deprecated
    -0.06
     combination
    -0.06
     obedience
    -0.06
     sacrifices
    -0.06
     eminent
    -0.06
    POSITIVE LOGITS
    .success
    0.07
    -----------
↵
    0.07
     yapılacak
    0.06
     Pete
    0.06
     αλλά
    0.06
     pym
    0.06
     داو
    0.06
    SearchParams
    0.06
    .result
    0.06
     왜
    0.06
    Act Density 0.018%

    No Known Activations