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

    Neuronpedia

    INDEX
    Explanations

    onset of conditions or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    -3.44
     was
    -2.94
    {
    -2.73
    M
    -2.53
    a
    -2.48
    <
    -2.39
    //(
    -2.36
    的问
    -2.34
    N
    -2.20
    //[
    -2.17
    POSITIVE LOGITS
    ſu
    2.83
    ࿚
    2.48
    谖
    2.44
     nowych
    2.39
    翆
    2.34
    괘
    2.31
    2.30
    ⬥
    2.23
    遯
    2.22
     tuviera
    2.17
    Act Density 0.005%

    No Known Activations