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

    Neuronpedia

    INDEX
    Explanations

    Math and logic questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    しっかり
    -0.08
    桌上
    -0.07
    wództw
    -0.07
    报记者
    -0.07
    =end
    -0.07
     republican
    -0.07
     anonymously
    -0.07
    .dw
    -0.07
     lecken
    -0.07
     Produced
    -0.06
    POSITIVE LOGITS
    Dog
    0.07
     Says
    0.07
     CLEAR
    0.07
     Rolls
    0.07
    兴起
    0.07
     ран
    0.07
     LocalDate
    0.06
    PROCESS
    0.06
     прав
    0.06
     exotic
    0.06
    Act Density 0.037%

    No Known Activations