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

    Neuronpedia

    INDEX
    Explanations

    edge of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     грани
    0.39
     purpos
    0.38
    Laurent
    0.37
     mengungkap
    0.37
    Lav
    0.37
     lactis
    0.36
    Pur
    0.35
     людей
    0.35
     गिवन
    0.35
    най
    0.35
    POSITIVE LOGITS
    σή
    0.37
    ವ
    0.36
     اوس
    0.36
     रीडिंग
    0.36
    ioon
    0.35
    ión
    0.35
    诤
    0.35
    笈
    0.35
    apiKey
    0.35
     einf
    0.34
    Act Density 0.000%

    No Known Activations