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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marvin
    -0.07
     submission
    -0.07
    ≦
    -0.06
     />
    -0.06
     CPP
    -0.06
    突出问题
    -0.06
    -0.06
     ATK
    -0.06
     anch
    -0.06
    uren
    -0.06
    POSITIVE LOGITS
     Beans
    0.08
    кал
    0.07
     وب
    0.07
    -vars
    0.07
    constant
    0.07
     Generates
    0.07
     wanted
    0.07
     Folding
    0.07
     постоян
    0.06
     일반
    0.06
    Act Density 0.011%

    No Known Activations