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

    Neuronpedia

    INDEX
    Explanations

    lists specific topics or subsequent questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ?,
    1.55
     ?)
    1.37
     ??
    1.31
     ?”
    1.30
    ?,
    1.23
     ?"
    1.23
    ？”
    1.22
    ?:
    1.20
     ?
    1.16
    ?.
    1.14
    POSITIVE LOGITS
    および
    0.74
     وب
    0.72
     ("[
    0.72
     específicos
    0.72
    óny
    0.71
     anciens
    0.71
     ("
    0.70
     и
    0.70
     وإ
    0.68
     ulteriori
    0.67
    Act Density 0.051%

    No Known Activations