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

    Neuronpedia

    INDEX
    Explanations

    AI puns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    为此
    0.43
    Stars
    0.42
    Flora
    0.42
    Kim
    0.41
    也在
    0.41
    }}^{*}
    0.40
    ения
    0.40
    優
    0.40
     उत्‍
    0.40
    Such
    0.40
    POSITIVE LOGITS
     sorun
    0.47
    ту
    0.46
     velike
    0.46
     erstmals
    0.46
    疠
    0.46
     économiques
    0.45
     attenzione
    0.45
    гар
    0.44
     கிரேக்க
    0.44
    ilateral
    0.44
    Act Density 0.010%

    No Known Activations