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

    Neuronpedia

    INDEX
    Explanations

    CJ, Month, or quarter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    노
    0.54
    தல
    0.47
    க
    0.46
    爱
    0.46
    发
    0.45
    了一些
    0.45
    லா
    0.44
    诺
    0.44
    迟
    0.42
    త
    0.42
    POSITIVE LOGITS
     FIXED
    0.52
    sized
    0.50
     suo
    0.49
     розпо
    0.49
    ,’’
    0.49
     accol
    0.48
     abhiv
    0.48
     adhipp
    0.47
    siz
    0.47
     vitth
    0.47
    Act Density 0.000%

    No Known Activations