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

    Neuronpedia

    INDEX
    Explanations

    is important and possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पण
    0.71
    webElementGuid
    0.68
    fprintf
    0.67
     excellence
    0.66
    excellence
    0.66
    ೆಗೆ
    0.65
     อ่าน
    0.64
    manship
    0.64
    heavy
    0.63
    IndexOf
    0.63
    POSITIVE LOGITS
    ட்சத்திர
    0.85
    і
    0.73
    ی
    0.71
    ة
    0.67
    jším
    0.67
    नुसार
    0.66
    ging
    0.66
    िनी
    0.66
    ال
    0.66
    ила
    0.65
    Act Density 0.095%

    No Known Activations