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

    Neuronpedia

    INDEX
    Explanations

    ub/Lub

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ┃
    -0.07
    soup
    -0.07
    INSERT
    -0.06
    OUSE
    -0.06
    े।
    -0.06
    *****↵↵
    -0.06
     Rails
    -0.06
    Serv
    -0.06
    STRUCT
    -0.06
    .GetString
    -0.06
    POSITIVE LOGITS
     Brun
    0.07
    field
    0.07
    County
    0.07
     สถาน
    0.06
     کش
    0.06
     Buk
    0.06
    اری
    0.06
     برابر
    0.06
    Brun
    0.06
     αγα
    0.06
    Act Density 0.001%

    No Known Activations