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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Delay
    -0.06
    学会
    -0.06
    -delay
    -0.06
     simil
    -0.06
     Step
    -0.06
     Certified
    -0.06
    /**↵↵
    -0.05
     возраст
    -0.05
     tenth
    -0.05
    .Le
    -0.05
    POSITIVE LOGITS
     دين
    0.07
    _countries
    0.07
     translate
    0.07
    (END
    0.06
    Execute
    0.06
    935
    0.06
    ixels
    0.06
    085
    0.06
    Queries
    0.06
    emos
    0.06
    Act Density 0.001%

    No Known Activations