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

    Neuronpedia

    INDEX
    Explanations

    analyst ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যুক্তি
    0.42
    ッター
    0.40
     멤버
    0.40
    メンバー
    0.40
     appellants
    0.39
    <footer>
    0.39
    ंड
    0.39
    institute
    0.39
    만에
    0.38
    Execution
    0.38
    POSITIVE LOGITS
    asal
    0.46
     extrapolate
    0.45
     grades
    0.43
     ratings
    0.41
    ß
    0.39
     Ана
    0.38
     Anal
    0.38
    Ана
    0.38
     sample
    0.38
    Anal
    0.38
    Act Density 0.003%

    No Known Activations