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

    Neuronpedia

    INDEX
    Explanations

    moves/turn/transfers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    poste
    0.48
     گاه
    0.43
     വിവര
    0.42
    粆
    0.41
    wallepics
    0.40
    侙
    0.40
    矨
    0.40
    actéristiques
    0.39
    Sophia
    0.39
     చివరి
    0.38
    POSITIVE LOGITS
     fourteen
    0.41
     twelve
    0.39
     choke
    0.38
     Fourteen
    0.38
     douze
    0.36
    Twelve
    0.36
     spade
    0.36
     Twelve
    0.35
      
    0.35
    楓
    0.34
    Act Density 0.000%

    No Known Activations