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

    Neuronpedia

    INDEX
    Explanations

    to learn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (summary
    -0.07
     fuels
    -0.07
     tapes
    -0.07
    spNet
    -0.07
    ..↵↵↵↵
    -0.06
    avr
    -0.06
     Screens
    -0.06
     COLORS
    -0.06
    -db
    -0.06
     klim
    -0.06
    POSITIVE LOGITS
    ảo
    0.07
     metrics
    0.06
    376
    0.06
    ařilo
    0.06
    "],["
    0.06
    _waiting
    0.06
     deterioration
    0.06
    legates
    0.06
     Consequently
    0.06
     Lawrence
    0.05
    Act Density 0.018%

    No Known Activations