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

    Neuronpedia

    INDEX
    Explanations

    Big

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dale
    -0.55
    LISTS
    -0.54
    ilder
    -0.54
     loophole
    -0.54
    ometra
    -0.54
    loop
    -0.52
    bol
    -0.51
    Tro
    -0.50
    udis
    -0.50
    hyrchwyd
    -0.50
    POSITIVE LOGITS
    TagMode
    0.72
    Personendaten
    0.63
    WriteBarrier
    0.59
     skolan
    0.56
     дописавши
    0.55
     wireType
    0.53
    =$?
    0.52
    LookAnd
    0.51
    ++]=
    0.50
    تقاوى
    0.49
    Act Density 0.008%

    No Known Activations