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

    Neuronpedia

    INDEX
    Explanations

    say "wake" variations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Issue
    -0.08
     Issue
    -0.07
     stems
    -0.06
    ')↵↵↵
    -0.06
     detained
    -0.06
    ób
    -0.06
    ，被
    -0.06
     sont
    -0.06
     rushed
    -0.06
    sahuje
    -0.06
    POSITIVE LOGITS
    วล
    0.07
    cpp
    0.07
     公
    0.06
     danych
    0.06
    �
    0.06
    Cc
    0.06
    �
    0.06
    .desktop
    0.06
    _terms
    0.06
    ghest
    0.06
    Act Density 0.037%

    No Known Activations