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

    Neuronpedia

    INDEX
    Explanations

    challenge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     challenge
    -1.82
     challenges
    -1.57
    challenge
    -1.48
    Challenge
    -1.46
     Challenge
    -1.44
     Challenges
    -1.40
     CHALLENGE
    -1.37
    challenges
    -1.30
    Challenges
    -1.27
     challenging
    -1.22
    POSITIVE LOGITS
    клопе
    0.82
    elemField
    0.78
    رشف
    0.75
    aarrggbb
    0.74
     utafitiHapana
    0.74
     autorytatywna
    0.72
    verwijspagina
    0.71
    AutoresizingMask
    0.71
    日閲覧
    0.70
     cherchés
    0.70
    Act Density 0.097%

    No Known Activations