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

    Neuronpedia

    INDEX
    Explanations

    requires or needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ರಳ
    0.32
     ಕಳೆದ
    0.30
    0.29
    ネルギー
    0.29
    挑戦
    0.29
    OTH
    0.29
    퐶
    0.28
     mencipt
    0.28
    निम्नलिखित
    0.27
     จง
    0.27
    POSITIVE LOGITS
    ,
    0.38
     inside
    0.36
    ↵
    0.35
     Inside
    0.32
     requires
    0.32
    /
    0.30
     Molecular
    0.30
     Require
    0.30
    :
    0.29
     Requires
    0.29
    Act Density 0.067%

    No Known Activations