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

    Neuronpedia

    INDEX
    Explanations

    offering support and help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Characteristics
    0.81
     Cloning
    0.71
     Induced
    0.71
     variously
    0.71
     cerebrospinal
    0.69
    AppDelegate
    0.69
    ↵
    0.69
    áver
    0.68
     manipulations
    0.68
     effettuare
    0.68
    POSITIVE LOGITS
     empowering
    1.11
     voices
    1.04
     inclusivity
    1.04
     transparency
    0.99
     empower
    0.98
     awareness
    0.97
    きちんと
    0.97
     accessible
    0.95
     rightful
    0.94
     empowerment
    0.93
    Act Density 0.233%

    No Known Activations