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

    Neuronpedia

    INDEX
    Explanations

    not everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ിലാണ്
    0.40
     yerine
    0.39
    karma
    0.38
     librería
    0.37
    Interfaz
    0.36
     부분이
    0.36
     ಪುಟ
    0.36
     Израи
    0.35
    ライ
    0.35
     হাফ
    0.35
    POSITIVE LOGITS
     Nog
    0.45
     MUS
    0.43
    必需
    0.43
     USER
    0.41
     नाव
    0.41
    oscopes
    0.41
     increasingly
    0.40
     często
    0.40
     अक्सर
    0.39
     MATTER
    0.39
    Act Density 0.002%

    No Known Activations