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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EXCEPTION
    -0.08
    Go
    -0.07
    Just
    -0.06
    ُن
    -0.06
    (units
    -0.06
    vc
    -0.06
     CX
    -0.06
     goto
    -0.06
     soften
    -0.06
    .want
    -0.06
    POSITIVE LOGITS
     outras
    0.06
    lsx
    0.06
    ịp
    0.06
     goddess
    0.06
    个
    0.06
     sleeves
    0.06
     proposal
    0.06
    交流
    0.06
    /music
    0.06
    _INCLUDE
    0.06
    Act Density 0.021%

    No Known Activations