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

    Neuronpedia

    INDEX
    Explanations

    words following certain verbs/nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISH
    0.52
     Zuge
    0.50
    oge
    0.50
    AM
    0.49
    MON
    0.49
    Am
    0.47
    AN
    0.45
    Ig
    0.45
    ANK
    0.45
    Um
    0.44
    POSITIVE LOGITS
     personnelles
    0.54
    lerinin
    0.49
     comandos
    0.46
    າດ
    0.46
     опи
    0.46
     opini
    0.46
     argumentos
    0.46
    ivided
    0.45
     मैट्रिक्स
    0.45
    рных
    0.45
    Act Density 0.000%

    No Known Activations