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

    Neuronpedia

    INDEX
    Explanations

    ChatGPT, bargaining, choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    กว่า
    0.43
    ')))
    0.42
    ishman
    0.41
     ा
    0.41
    вої
    0.41
    FlashValue
    0.40
    ByURL
    0.40
    ineuse
    0.40
    רות
    0.39
    Uh
    0.38
    POSITIVE LOGITS
     Ais
    0.50
     Binder
    0.49
     Streets
    0.49
    kinson
    0.46
    漫畫
    0.45
     metter
    0.45
     bargaining
    0.45
     Ait
    0.45
     Waters
    0.44
     Theatre
    0.44
    Act Density 0.006%

    No Known Activations