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

    Neuronpedia

    INDEX
    Explanations

    indicating an alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nouns
    0.43
    ምና
    0.41
     fichiers
    0.39
     nouns
    0.39
     skladu
    0.38
     nozzles
    0.38
     ਅਤੇ
    0.38
     ارزش
    0.38
     hiver
    0.37
     journaliste
    0.37
    POSITIVE LOGITS
     Alternatively
    0.56
    Alternatively
    0.52
     Perseverance
    0.44
     वैकल्पिक
    0.44
     alternate
    0.43
     alterna
    0.43
     lam
    0.43
     compensatory
    0.43
    ]
    0.43
    ?”
    0.43
    Act Density 0.001%

    No Known Activations