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

    Neuronpedia

    INDEX
    Explanations

    url and protocol separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.55
    Ut
    0.49
    Ox
    0.46
    umbles
    0.46
    lox
    0.44
    ay
    0.44
    و
    0.43
    Nex
    0.43
    -
    0.43
    Utilities
    0.43
    POSITIVE LOGITS
     фактически
    0.56
     политики
    0.53
    риал
    0.51
     núi
    0.50
    జా
    0.47
    彠
    0.47
     revel
    0.47
     envers
    0.47
    ລະ
    0.47
     apos
    0.47
    Act Density 0.001%

    No Known Activations