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

    Neuronpedia

    INDEX
    Explanations

    at Google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cascade
    0.42
     Wsp
    0.40
    CHEM
    0.39
    津
    0.39
     BOC
    0.38
     رائے
    0.37
    ಳೆ
    0.36
     Bock
    0.36
     crust
    0.36
    瀣
    0.36
    POSITIVE LOGITS
     toler
    0.42
     tolerated
    0.41
    amac
    0.38
     tolerate
    0.37
     utili
    0.37
    inki
    0.37
    ແມ
    0.36
    Tolerance
    0.36
    clientY
    0.36
     tolerance
    0.35
    Act Density 0.014%

    No Known Activations