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

    Neuronpedia

    INDEX
    Explanations

    offers and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legality
    0.86
     legislação
    0.80
     LIT
    0.79
     accessibility
    0.78
     compliance
    0.77
    down
    0.76
     ATL
    0.76
     nid
    0.76
     corrig
    0.76
     tsunami
    0.75
    POSITIVE LOGITS
     daß
    0.56
     हा
    0.55
    skich
    0.53
     Sign
    0.53
     Spins
    0.52
    uska
    0.50
     Card
    0.50
     Videos
    0.49
    DefineConstants
    0.49
    Required
    0.49
    Act Density 0.000%

    No Known Activations