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

    Neuronpedia

    INDEX
    Explanations

    lists for what is wanted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Depending
    0.42
    ною
    0.39
    Ю
    0.39
    τή
    0.38
    Thin
    0.38
    িকারী
    0.37
     nemmeno
    0.37
    ávy
    0.37
     عالم
    0.37
    Full
    0.37
    POSITIVE LOGITS
     prosa
    0.45
    IsMethod
    0.41
    resposta
    0.41
    arankan
    0.40
     Labrenzia
    0.40
     sowas
    0.39
     claro
    0.38
    henge
    0.38
    perti
    0.38
     posta
    0.38
    Act Density 0.021%

    No Known Activations