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

    Neuronpedia

    INDEX
    Explanations

    modular approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आतंकवादी
    0.68
     मूर्ति
    0.59
     bodyguard
    0.58
     third
    0.58
     Martyr
    0.57
    कीन
    0.57
     या
    0.56
     महिला
    0.56
    őtt
    0.55
     Celebrity
    0.55
    POSITIVE LOGITS
     each
    1.63
    Each
    1.59
     Each
    1.56
    each
    1.56
    每个
    1.51
    แต่ละ
    1.45
     каждая
    1.36
    每個
    1.35
     ഓരോ
    1.35
     jednotliv
    1.35
    Act Density 1.154%

    No Known Activations