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

    Neuronpedia

    INDEX
    Explanations

    hotline URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVertical
    0.39
    꽉
    0.38
     როგორ
    0.37
    દાન
    0.36
    ethoscope
    0.35
    list
    0.35
     recorrido
    0.35
     দূত
    0.35
    сур
    0.35
    amber
    0.35
    POSITIVE LOGITS
     per
    0.52
     NPR
    0.38
     Cosm
    0.37
     area
    0.37
     po
    0.37
     Per
    0.36
    ποι
    0.36
     Bravo
    0.36
    屹
    0.36
     CNN
    0.36
    Act Density 0.131%

    No Known Activations