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

    Neuronpedia

    INDEX
    Explanations

    python3 script interpreter headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agreg
    1.05
     Hebre
    1.03
    ၡ
    0.92
    м
    0.91
     Quang
    0.91
     ispit
    0.91
    حدیث
    0.89
    $=\
    0.89
     Sasaki
    0.88
     añad
    0.88
    POSITIVE LOGITS
    ä
    1.31
     python
    1.03
    .
    0.97
    ari
    0.93
    ala
    0.93
    ills
    0.92
    us
    0.91
    ond
    0.89
    ana
    0.89
    ich
    0.88
    Act Density 0.008%

    No Known Activations