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

    Neuronpedia

    INDEX
    Explanations

    numbers and slash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sms
    0.52
    ंबई
    0.51
     TComponent
    0.50
     Taxonomic
    0.47
    agation
    0.46
     rjf
    0.45
    の原因
    0.45
    的区别
    0.45
     Hãy
    0.44
     SwitchCompat
    0.44
    POSITIVE LOGITS
    ك
    0.64
     médecin
    0.49
    ط
    0.48
     waar
    0.48
     verdens
    0.48
     му
    0.47
     médecins
    0.46
     Meer
    0.45
     hoofd
    0.45
     मैट्र
    0.45
    Act Density 0.000%

    No Known Activations