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

    Neuronpedia

    INDEX
    Explanations

    Perry, size, plays, Admin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    которые
    2.46
     tirelessly
    2.45
    kbeta
    2.44
     preclude
    2.36
    Diary
    2.31
    𝖘
    2.28
    יות
    2.28
     recalled
    2.24
     IntVar
    2.24
     testname
    2.23
    POSITIVE LOGITS
    에
    2.16
    ر
    1.87
    Cs
    1.61
    त
    1.60
    й
    1.54
    1.50
    值为
    1.49
    在
    1.46
    のも
    1.46
    ン
    1.44
    Act Density 0.001%

    No Known Activations