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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dj
    0.54
     Dj
    0.52
     DJ
    0.51
    ⟋
    0.49
     Detroit
    0.48
    Dj
    0.48
     resid
    0.47
     elektron
    0.47
     remixes
    0.47
     remix
    0.46
    POSITIVE LOGITS
    ssymb
    0.42
    Retired
    0.39
     সম্পাদক
    0.39
    昭
    0.38
     آپ
    0.36
    prev
    0.36
    昭和
    0.36
    ChooserView
    0.35
    tac
    0.34
     TMZ
    0.34
    Act Density 0.022%

    No Known Activations