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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jedno
    -0.08
    警
    -0.07
    砂
    -0.06
     proud
    -0.06
    .seconds
    -0.06
     la
    -0.06
     cabo
    -0.06
     shower
    -0.06
     Away
    -0.06
     neighborhoods
    -0.06
    POSITIVE LOGITS
    391
    0.07
    сих
    0.07
    Newsletter
    0.06
    ered
    0.06
     Economist
    0.06
    system
    0.06
    tparam
    0.06
     خط
    0.06
    review
    0.06
     용
    0.06
    Act Density 0.000%

    No Known Activations