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

    Neuronpedia

    INDEX
    Explanations

    names and specific subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    呫
    0.39
     करा
    0.39
     Ebony
    0.38
    痈
    0.37
    вища
    0.37
    ()['
    0.37
    患
    0.37
    髯
    0.37
    体験
    0.37
    зера
    0.37
    POSITIVE LOGITS
    bes
    0.45
     bes
    0.43
     nic
    0.42
     Bes
    0.41
     slowed
    0.41
     payment
    0.40
    cartes
    0.40
     fre
    0.39
     خاص
    0.39
     characteristic
    0.38
    Act Density 0.000%

    No Known Activations