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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بشر
    -0.06
    92
    -0.06
    ReturnValue
    -0.06
     하면
    -0.06
     براي
    -0.06
     birçok
    -0.06
     Stokes
    -0.06
     Các
    -0.06
    诉
    -0.06
    Vars
    -0.06
    POSITIVE LOGITS
     FONT
    0.07
    ":-
    0.06
    กล
    0.06
     guerr
    0.06
     Afghan
    0.06
     фин
    0.06
     SUB
    0.06
    ULT
    0.06
     screened
    0.06
    uhl
    0.06
    Act Density 0.238%

    No Known Activations