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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    domain
    -0.07
    .ErrorCode
    -0.06
    WithEmail
    -0.06
    Titles
    -0.06
    _extended
    -0.06
     STUD
    -0.06
    EMPL
    -0.06
    Norm
    -0.06
     evolved
    -0.06
     CLEAN
    -0.06
    POSITIVE LOGITS
     болезни
    0.06
     pov
    0.06
     "))
    0.06
    ส
    0.06
     вещества
    0.06
    mi
    0.06
     spectacle
    0.06
     champ
    0.06
     vergi
    0.06
    อเมร
    0.06
    Act Density 0.019%

    No Known Activations