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

    Neuronpedia

    INDEX
    Explanations

    networking topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Factors
    0.61
     submer
    0.60
     பண்ட
    0.57
    ADA
    0.56
    CEPT
    0.56
    Factors
    0.56
    ament
    0.55
    band
    0.55
     factors
    0.55
     obesity
    0.55
    POSITIVE LOGITS
    мові
    0.64
     tiế
    0.58
    мови
    0.56
     наи
    0.54
     tiek
    0.53
     गवा
    0.53
     earns
    0.52
    🔗
    0.52
     chacun
    0.51
     vipp
    0.51
    Act Density 0.000%

    No Known Activations