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

    Neuronpedia

    INDEX
    Explanations

    dependence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proactive
    -0.07
     else
    -0.07
    Courses
    -0.07
     Chocolate
    -0.07
     usar
    -0.07
    urst
    -0.07
     satisfaction
    -0.07
     Uhr
    -0.07
    ขนาด
    -0.06
     chocolate
    -0.06
    POSITIVE LOGITS
     dependence
    0.09
    .px
    0.07
     VARIABLE
    0.06
    .awt
    0.06
    .IC
    0.06
    jl
    0.06
     hone
    0.06
     Соб
    0.06
    .AUTH
    0.06
     eup
    0.06
    Act Density 0.011%

    No Known Activations