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

    Neuronpedia

    INDEX
    Explanations

    real money, for free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Realistic
    0.57
     Realistic
    0.55
    realistic
    0.52
    reality
    0.49
     realistic
    0.47
    ayment
    0.46
    Reality
    0.46
     Reality
    0.46
     unrealistic
    0.43
    ainless
    0.42
    POSITIVE LOGITS
     dummies
    0.41
    colspan
    0.39
    葷
    0.38
     linux
    0.37
    ivam
    0.36
     fun
    0.35
     dummy
    0.35
    κη
    0.35
     Crock
    0.35
     keeps
    0.35
    Act Density 0.002%

    No Known Activations