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

    Neuronpedia

    INDEX
    Explanations

    locations and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     குறிப்பிட்ட
    0.40
     vuelto
    0.38
     pairing
    0.36
     biến
    0.36
    ৩
    0.36
    poruč
    0.35
    ̃
    0.35
     ανε
    0.35
    قي
    0.35
     folosit
    0.35
    POSITIVE LOGITS
    곳
    0.71
     Place
    0.68
     Places
    0.68
     place
    0.68
     lugar
    0.66
     PLACE
    0.66
     places
    0.64
    Place
    0.64
    PLACE
    0.63
     جگہ
    0.63
    Act Density 0.030%

    No Known Activations