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

    Neuronpedia

    INDEX
    Explanations

    technical documentation descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CHEMISTRY
    0.49
     Bankruptcy
    0.48
    ля
    0.42
     Epidemiology
    0.42
    Bankruptcy
    0.41
     META
    0.41
     Chemistry
    0.40
    的企业
    0.40
     remembering
    0.40
     UNIVERSITY
    0.40
    POSITIVE LOGITS
    dent
    0.56
     sere
    0.52
     usar
    0.49
    possible
    0.49
     caracteriza
    0.49
    slightly
    0.49
    smoked
    0.49
    desired
    0.49
     cordial
    0.48
    टेस्ट
    0.47
    Act Density 0.000%

    No Known Activations