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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kø
    -0.07
    魂
    -0.06
     leer
    -0.06
     دون
    -0.06
    泊
    -0.06
    YK
    -0.06
     wings
    -0.06
    /")
    -0.06
     wing
    -0.06
     skutečně
    -0.06
    POSITIVE LOGITS
     Sons
    0.07
    BUF
    0.06
    مد
    0.06
    _PW
    0.06
    DownList
    0.06
     سعر
    0.06
    .Ş
    0.06
    uvre
    0.06
     AFP
    0.06
     Awake
    0.06
    Act Density 0.206%

    No Known Activations