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

    Neuronpedia

    INDEX
    Explanations

    adjusting settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manipulate
    0.70
     lasso
    0.64
     bandage
    0.59
     moment
    0.57
     synthesized
    0.57
    ⁹
    0.57
     class
    0.56
     memory
    0.56
    ৯
    0.56
     debug
    0.55
    POSITIVE LOGITS
    is
    1.02
    on
    0.85
    settings
    0.77
    setting
    0.71
    ’
    0.70
    to
    0.70
    preferences
    0.69
    as
    0.68
    Settings
    0.68
    Setting
    0.66
    Act Density 0.028%

    No Known Activations