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

    Neuronpedia

    INDEX
    Explanations

    Online game-related content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מקצוע
    -0.08
    crypto
    -0.08
    Cleaning
    -0.07
     Macros
    -0.07
     Tantra
    -0.07
     Tobacco
    -0.07
     dresser
    -0.07
     chicago
    -0.07
     lettuce
    -0.07
    َا
    -0.07
    POSITIVE LOGITS
    귀
    0.08
    .Scale
    0.08
    .show
    0.07
    눅
    0.07
     명
    0.07
     hơn
    0.07
    _EP
    0.07
    Sie
    0.07
    .take
    0.07
     `'
    0.07
    Act Density 0.061%

    No Known Activations