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

    Neuronpedia

    INDEX
    Explanations

    function definition keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enkelt
    0.41
     adjust
    0.40
     interpret
    0.38
     conclus
    0.38
     attendant
    0.37
    ന്യാ
    0.37
     adjusts
    0.37
     evalu
    0.36
     imprison
    0.36
     delt
    0.36
    POSITIVE LOGITS
    на
    0.50
    an
    0.49
    k
    0.48
     começou
    0.47
    quela
    0.46
    에
    0.44
     Поэтому
    0.42
    ară
    0.42
    ра
    0.41
    zelfde
    0.41
    Act Density 0.000%

    No Known Activations