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

    Neuronpedia

    INDEX
    Explanations

    significant risk, governance, decline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enido
    0.43
     Streptococcus
    0.41
     Mois
    0.40
     gneiss
    0.38
    gren
    0.38
    Compensation
    0.38
     Compensation
    0.36
     брон
    0.36
     müsste
    0.35
     moeten
    0.35
    POSITIVE LOGITS
    Luc
    0.40
    ामु
    0.40
     Harley
    0.39
     ws
    0.39
     luckily
    0.38
    Pose
    0.37
     suggested
    0.37
     бар
    0.37
     Emilia
    0.37
    surprisingly
    0.37
    Act Density 0.000%

    No Known Activations