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

    Neuronpedia

    INDEX
    Explanations

    ambitious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    0.48
    Ｔ
    0.46
    3
    0.46
    G
    0.46
    C
    0.45
    icals
    0.45
    icious
    0.45
    phones
    0.44
    ikal
    0.43
    S
    0.43
    POSITIVE LOGITS
    𒌑
    0.51
     perché
    0.45
    новништво
    0.44
    ائلة
    0.43
    𒆳
    0.43
     menschen
    0.42
    स्तेमाल
    0.42
    setInt
    0.42
     straordin
    0.42
    0.42
    Act Density 0.004%

    No Known Activations