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

    Neuronpedia

    INDEX
    Explanations

    ghost masters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പറ
    0.38
     umur
    0.38
    নিয়া
    0.38
    gård
    0.37
     রাম
    0.36
    ándor
    0.36
    .~
    0.36
     краё
    0.36
     endian
    0.36
     köpek
    0.36
    POSITIVE LOGITS
     ghost
    0.79
     Ghost
    0.76
     Masters
    0.66
    Ghost
    0.64
    ghost
    0.63
     Gb
    0.61
    Masters
    0.60
     gb
    0.58
     masters
    0.57
     Writers
    0.56
    Act Density 0.001%

    No Known Activations