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

    Neuronpedia

    INDEX
    Explanations

    risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dispatch
    -0.07
    olle
    -0.06
    ịa
    -0.06
     towns
    -0.06
    .Canvas
    -0.06
    ้ว
    -0.06
    Stuff
    -0.06
    #w
    -0.06
    AXB
    -0.06
    *****/↵
    -0.06
    POSITIVE LOGITS
    knowledge
    0.07
     Risk
    0.06
    ercial
    0.06
     väl
    0.06
     generalized
    0.06
     паль
    0.06
     possessing
    0.06
     intimately
    0.06
    699
    0.06
     نه
    0.06
    Act Density 0.013%

    No Known Activations