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

    Neuronpedia

    INDEX
    Explanations

    doubt, presumably, undoubtedly, presume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ca
    0.56
     testers
    0.55
    racellular
    0.55
    ierz
    0.54
    classe
    0.53
    ClassName
    0.52
     রাধানাথ
    0.51
    ías
    0.51
    ça
    0.50
    rž
    0.49
    POSITIVE LOGITS
     بسته
    0.61
     lalu
    0.58
    那你
    0.54
    ප
    0.52
    Ｓ
    0.52
     weaponry
    0.52
    ামত
    0.50
     offen
    0.50
    ਪਣ
    0.50
    )?
    0.49
    Act Density 0.001%

    No Known Activations