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

    Neuronpedia

    INDEX
    Explanations

    logic and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hospitable
    0.47
    Ｖ
    0.46
     DENUMIRE
    0.45
    idah
    0.45
     Scorpion
    0.44
     軍
    0.44
     village
    0.43
    랜드
    0.43
     scorpion
    0.43
    ხვევ
    0.43
    POSITIVE LOGITS
    न
    0.58
    н
    0.52
    0.51
    ン
    0.49
     aktive
    0.48
     antibiot
    0.47
    ẫu
    0.45
    amy
    0.43
    atorii
    0.43
    i
    0.43
    Act Density 0.000%

    No Known Activations