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

    Neuronpedia

    INDEX
    Explanations

    how it is used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     life
    0.35
    生命
    0.35
     diagnoses
    0.34
     الحياة
    0.34
     diagnosed
    0.32
    ère
    0.32
     transcripts
    0.32
    群体
    0.32
     жизнь
    0.31
    在这个
    0.31
    POSITIVE LOGITS
    bauen
    0.40
    boa
    0.39
     budou
    0.37
    jsce
    0.36
     wou
    0.36
    👆
    0.36
     trusty
    0.36
    ोंग
    0.36
    あくまで
    0.36
     bote
    0.35
    Act Density 0.007%

    No Known Activations