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

    Neuronpedia

    INDEX
    Explanations

    argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transmitted
    -0.06
     freedom
    -0.06
     beam
    -0.06
    _costs
    -0.06
     station
    -0.06
    bben
    -0.06
     dx
    -0.06
    imagen
    -0.06
    .FileInputStream
    -0.06
     freedoms
    -0.06
    POSITIVE LOGITS
    Lex
    0.07
     contentious
    0.07
    ürger
    0.07
     Firearms
    0.07
    ूष
    0.06
     \<^
    0.06
     argument
    0.06
    ryn
    0.06
     sắc
    0.06
     необ
    0.06
    Act Density 0.019%

    No Known Activations