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

    Neuronpedia

    INDEX
    Explanations

    discussion and debate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ni
    0.47
     It
    0.47
    ene
    0.45
    rie
    0.43
    ened
    0.41
    van
    0.41
    आईएस
    0.41
    st
    0.40
    ny
    0.40
    mail
    0.40
    POSITIVE LOGITS
    인
    0.55
     debates
    0.51
     disputa
    0.50
     negotiator
    0.50
    보다
    0.49
     disputes
    0.49
     adicionar
    0.48
    وی
    0.47
    ุ
    0.47
    мови
    0.47
    Act Density 0.538%

    No Known Activations