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

    Neuronpedia

    INDEX
    Explanations

    languages and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र्
    0.56
    mos
    0.52
    š
    0.52
    ordon
    0.51
     대신
    0.51
    g
    0.49
    heten
    0.49
    heds
    0.49
    helle
    0.48
    idane
    0.47
    POSITIVE LOGITS
     seeker
    0.69
     newbies
    0.59
     Australian
    0.58
     Polyester
    0.58
     chum
    0.58
     newbie
    0.58
     önemlidir
    0.58
     polyester
    0.57
    המ
    0.57
     natu
    0.57
    Act Density 0.000%

    No Known Activations