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

    Neuronpedia

    INDEX
    Explanations

    proper names followed by specific suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Möglich
    0.28
     Acá
    0.26
    ార్క్
    0.26
     możli
    0.25
     mandrel
    0.25
     إذا
    0.25
     അവിടെ
    0.24
     blanchâtre
    0.24
     mannit
    0.24
    ถ้า
    0.24
    POSITIVE LOGITS
    ag
    0.33
    -
    0.33
    un
    0.30
    '
    0.30
    ann
    0.30
    im
    0.29
    _
    0.29
    q
    0.29
    ’
    0.29
    ang
    0.29
    Act Density 0.140%

    No Known Activations