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

    Neuronpedia

    INDEX
    Explanations

    question words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可能性があります
    0.40
     plunder
    0.35
     கட்டமை
    0.34
    geoning
    0.33
    涜
    0.32
     generically
    0.32
     configurable
    0.32
     दिखता
    0.32
     pseudo
    0.31
     বৃদ্ধি
    0.31
    POSITIVE LOGITS
     IELTS
    0.45
    _______
    0.42
     TOEFL
    0.42
    ＿＿
    0.42
    .___
    0.37
    kelas
    0.37
     marido
    0.36
    ______
    0.36
    __________
    0.36
     tourists
    0.35
    Act Density 0.043%

    No Known Activations