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

    Neuronpedia

    INDEX
    Explanations

    improvements and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beelding
    0.32
     सभी
    0.32
    c
    0.31
    sciences
    0.30
    ോഗ
    0.29
     તમામ
    0.29
    are
    0.28
    naver
    0.28
    adh
    0.27
    ambil
    0.27
    POSITIVE LOGITS
    ↵↵↵↵
    0.35
    ↵↵
    0.34
     დროს
    0.32
    ר
    0.30
    能在
    0.30
    .
    0.30
     Monate
    0.30
    阶段
    0.29
    ↵↵↵
    0.29
    ்தான்
    0.29
    Act Density 0.055%

    No Known Activations