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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ล
    -0.07
     assigns
    -0.07
    wine
    -0.07
    ';↵↵↵
    -0.07
    rones
    -0.07
    ể
    -0.07
    AVOR
    -0.07
     TR
    -0.07
    @WebServlet
    -0.06
    IOD
    -0.06
    POSITIVE LOGITS
     Accom
    0.06
    मह
    0.06
    semester
    0.06
     richer
    0.06
     mar
    0.06
     CHAR
    0.06
     Admin
    0.06
    (artist
    0.06
    �
    0.06
     Nar
    0.06
    Act Density 0.021%

    No Known Activations