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

    Neuronpedia

    INDEX
    Explanations

    character encoding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，现在
    -0.07
    ाइव
    -0.07
     delicious
    -0.07
    Recognizer
    -0.07
     systemFontOfSize
    -0.07
    غة
    -0.06
     欧美
    -0.06
     Meer
    -0.06
    ш
    -0.06
    طن
    -0.06
    POSITIVE LOGITS
     BUFF
    0.06
     Baltic
    0.06
     thé
    0.06
    Adds
    0.06
    FLT
    0.06
     Rol
    0.06
    (open
    0.06
    /class
    0.06
    (CC
    0.06
    [],
    0.06
    Act Density 0.032%

    No Known Activations