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

    Neuronpedia

    INDEX
    Explanations

    context: **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ο
    0.48
     Shall
    0.47
    ここは
    0.45
     Ο
    0.45
     shall
    0.44
    shall
    0.43
     मछली
    0.43
     বেশকিছু
    0.43
    ╿
    0.43
    swürdig
    0.42
    POSITIVE LOGITS
    astar
    0.46
     library
    0.45
     Provider
    0.42
     Library
    0.42
    Library
    0.41
    able
    0.41
    द्दीन
    0.40
    ഗീയ
    0.40
     धोखा
    0.39
    Nat
    0.39
    Act Density 0.001%

    No Known Activations