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

    Neuronpedia

    INDEX
    Explanations

    web development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    も
    -0.07
     prob
    -0.07
    esity
    -0.07
    िस
    -0.06
    .t
    -0.06
     Rubber
    -0.06
     bozuk
    -0.06
    lili
    -0.06
     year
    -0.06
    -election
    -0.06
    POSITIVE LOGITS
    式
    0.06
    =find
    0.06
     překlad
    0.06
     rebell
    0.06
    Modes
    0.06
     ontvang
    0.06
     расс
    0.06
    (thing
    0.06
    译
    0.06
     reminds
    0.06
    Act Density 0.083%

    No Known Activations