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

    Neuronpedia

    INDEX
    Explanations

    edit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _STR
    -0.06
     extraordinary
    -0.06
     Dart
    -0.06
     Bu
    -0.06
     looming
    -0.06
    、ア
    -0.06
     Scenes
    -0.06
     Harbour
    -0.06
    Nx
    -0.06
    反应
    -0.06
    POSITIVE LOGITS
     труб
    0.07
    GRADE
    0.07
     Vietnam
    0.06
    іч
    0.06
    ').'</
    0.06
    perl
    0.06
     vinden
    0.06
    ARS
    0.06
    snow
    0.06
     whenever
    0.06
    Act Density 0.025%

    No Known Activations