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

    Neuronpedia

    INDEX
    Explanations

    version numbers in urls or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อายุ
    0.52
     appId
    0.44
    Edad
    0.44
     '.';
    0.43
    Usually
    0.42
    วัต
    0.41
     значений
    0.41
    裵
    0.41
     sebesar
    0.39
     "'";
    0.39
    POSITIVE LOGITS
    de
    0.68
    d
    0.59
    کام
    0.57
    ção
    0.52
    ie
    0.51
    z
    0.50
    with
    0.49
    lc
    0.48
    ｅ
    0.48
    +"
    0.48
    Act Density 0.008%

    No Known Activations