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

    Neuronpedia

    INDEX
    Explanations

    sw + common suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \
    -3.22
     The
    -2.61
    2
    -2.34
    1
    -2.34
    ものに
    -2.34
    al
    -2.28
    和你
    -2.27
    ⸫
    -2.23
     
    -2.22
     a
    -2.19
    POSITIVE LOGITS
     GenerationType
    2.55
    locene
    2.53
    ribune
    2.48
    uchos
    2.47
     情侣
    2.47
    LLocation
    2.42
    炱
    2.39
    thouses
    2.38
    ASTIC
    2.34
    MessageTagHelper
    2.34
    Act Density 0.029%

    No Known Activations