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

    Neuronpedia

    INDEX
    Explanations

    <!DOCTYPE html>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     النص
    0.51
    ágoras
    0.41
    ুরা
    0.40
    evidence
    0.39
    CCA
    0.38
    deg
    0.38
     সত্যা
    0.38
    chil
    0.38
    CBS
    0.37
    TSC
    0.37
    POSITIVE LOGITS
    <!
    1.02
     doctrine
    0.98
     Doctrine
    0.93
     doctrines
    0.86
     <!
    0.86
    doctrine
    0.80
    Doctrine
    0.80
     doct
    0.74
     doctrinal
    0.70
     Doct
    0.68
    Act Density 0.007%

    No Known Activations