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

    Neuronpedia

    INDEX
    Explanations

    technical acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Celsius
    0.71
    ]
    0.69
    SHE
    0.67
     lateribus
    0.67
    SK
    0.64
    SPE
    0.63
    \">
    0.63
    DOWNLOAD
    0.63
     yksi
    0.62
    ἆ
    0.61
    POSITIVE LOGITS
    ında
    0.80
    ューズ
    0.78
    ribute
    0.77
    ्रा
    0.74
     acronym
    0.70
    یا
    0.68
    ना
    0.68
    ergic
    0.68
    ttes
    0.67
    єю
    0.67
    Act Density 0.135%

    No Known Activations