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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    737
    -0.07
    .top
    -0.07
     Damage
    -0.07
    td
    -0.06
     nozzle
    -0.06
    %B
    -0.06
    _LIBRARY
    -0.06
     Patron
    -0.06
     damage
    -0.06
     patron
    -0.06
    POSITIVE LOGITS
    講
    0.07
    azers
    0.07
    急
    0.06
    .TabControl
    0.06
    Pl
    0.06
    isks
    0.06
    Apr
    0.06
     unintended
    0.06
    /'↵
    0.06
    Kn
    0.06
    Act Density 0.610%

    No Known Activations