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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with Master

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.44
     favours
    0.44
     favors
    0.42
    adə
    0.41
     лета
    0.40
    কান্ত
    0.39
    েও
    0.39
    eee
    0.39
    㸳
    0.39
     eint
    0.38
    POSITIVE LOGITS
     Master
    0.86
     MASTER
    0.84
     master
    0.84
    master
    0.79
    Master
    0.75
     masters
    0.75
    masters
    0.71
    MASTER
    0.66
     Masters
    0.66
     マスター
    0.65
    Act Density 0.010%

    No Known Activations