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

    Neuronpedia

    INDEX
    Explanations

    your company or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ברים
    0.42
    0.39
     Bolts
    0.38
     Arabs
    0.38
     ২০
    0.38
     Falcons
    0.37
     eggs
    0.37
     Parents
    0.37
     squats
    0.37
     cubs
    0.37
    POSITIVE LOGITS
    5
    0.59
    7
    0.46
    6
    0.44
    :
    0.42
    4
    0.39
    ς
    0.39
    .
    0.39
    ing
    0.38
    nya
    0.38
    um
    0.37
    Act Density 0.288%

    No Known Activations