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

    Neuronpedia

    INDEX
    Explanations

    playful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রায়
    0.77
    ikations
    0.72
    ving
    0.71
    ilte
    0.70
     started
    0.70
    ارم
    0.69
    门的
    0.69
    ставля
    0.69
     Satisfaction
    0.69
     Posting
    0.69
    POSITIVE LOGITS
    wright
    0.99
    fulness
    0.88
    dough
    0.87
     coy
    0.84
     guitar
    0.82
    acting
    0.82
    Guitar
    0.82
    dates
    0.80
    ந
    0.75
     rôle
    0.74
    Act Density 0.073%

    No Known Activations