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

    Neuronpedia

    INDEX
    Explanations

    messy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hiệp
    0.36
    dokka
    0.35
    屈
    0.35
    nDims
    0.35
    َنْ
    0.34
    icida
    0.33
     dạ
    0.33
    ulkar
    0.33
    InsertInt
    0.33
    סטר
    0.33
    POSITIVE LOGITS
     mess
    3.52
     messy
    3.16
     Mess
    3.08
    mess
    3.06
    Mess
    3.03
     messes
    2.86
     MESS
    2.61
     messing
    2.03
     messed
    1.85
     messen
    1.82
    Act Density 0.024%

    No Known Activations