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

    Neuronpedia

    INDEX
    Explanations

    Foreign words and codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occup
    -0.07
     xmlns
    -0.07
    Heading
    -0.07
    そう
    -0.07
     points
    -0.07
    Α
    -0.07
     Sommer
    -0.07
     która
    -0.06
     fourth
    -0.06
     Wouldn
    -0.06
    POSITIVE LOGITS
     두
    0.07
    .userService
    0.06
    .PER
    0.06
    odzi
    0.06
    ISC
    0.06
    _cre
    0.06
    _APP
    0.06
     televizyon
    0.06
     Toll
    0.06
     sigue
    0.05
    Act Density 0.267%

    No Known Activations