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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incremental
    -0.07
     FUCK
    -0.06
    .assertNull
    -0.06
    zent
    -0.06
    odied
    -0.06
     apresent
    -0.06
    ALES
    -0.06
     fica
    -0.06
     Swimming
    -0.06
    DisplayName
    -0.06
    POSITIVE LOGITS
    .amazonaws
    0.07
    (Type
    0.06
    .Object
    0.06
     GetUser
    0.06
    .ComponentModel
    0.06
    [unit
    0.06
     UserModel
    0.06
    /native
    0.06
    ео
    0.06
    bons
    0.06
    Act Density 0.001%

    No Known Activations