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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mph
    -0.06
    =fopen
    -0.06
     jail
    -0.06
    ’ll
    -0.06
     deform
    -0.06
    ErrorResponse
    -0.06
    MR
    -0.06
     Воз
    -0.06
     probing
    -0.06
     MR
    -0.06
    POSITIVE LOGITS
     Maven
    0.08
     Nexus
    0.08
    space
    0.07
    431
    0.07
     spaces
    0.07
     PRIVATE
    0.07
    κά
    0.07
    "};↵↵
    0.07
    ivic
    0.07
     Space
    0.07
    Act Density 0.003%

    No Known Activations