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

    Neuronpedia

    INDEX
    Explanations

    internet-connected billboards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    部门
    0.51
     сезон
    0.50
     procédé
    0.50
     télé
    0.49
     início
    0.48
     théâtre
    0.48
     bateau
    0.47
    ängt
    0.47
    라마
    0.46
     kerül
    0.46
    POSITIVE LOGITS
     a
    0.55
    Cement
    0.52
    Co
    0.52
    Am
    0.52
    ل
    0.51
    CD
    0.51
    Cake
    0.50
    a
    0.50
    Obama
    0.49
    Reflection
    0.47
    Act Density 0.000%

    No Known Activations