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

    Neuronpedia

    INDEX
    Explanations

    YouTube searches for tutorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ,
    1.26
     (
    1.22
    ,
    1.21
    1.14
    ,(
    1.01
    6
    1.01
     +
    0.99
    2
    0.97
    (
    0.95
    7
    0.94
    POSITIVE LOGITS
     beban
    1.57
     debajo
    1.54
     puisi
    1.47
     särsk
    1.39
     significativo
    1.38
    পন্ন
    1.36
     silencio
    1.36
    señ
    1.36
     latihan
    1.35
     atteggi
    1.35
    Act Density 0.014%

    No Known Activations