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

    Neuronpedia

    INDEX
    Explanations

    start of phrases/sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     güzel
    0.97
     Ministère
    0.91
    非常的
    0.88
    parentElement
    0.86
     anthropogenic
    0.84
     içerisinde
    0.84
     सुन्दर
    0.81
     nuestra
    0.79
    🌿
    0.79
    ümüzde
    0.77
    POSITIVE LOGITS
     swagger
    0.86
     clout
    0.84
     booze
    0.76
     பிரச்
    0.76
     stets
    0.75
     toughest
    0.74
     relentlessly
    0.71
     whack
    0.71
     dogged
    0.71
     bloke
    0.70
    Act Density 0.029%

    No Known Activations