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

    Neuronpedia

    INDEX
    Explanations

    russian words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "
↵
↵
    -0.07
    .Keyboard
    -0.07
     Narrow
    -0.07
    ORG
    -0.07
    .Col
    -0.07
    imating
    -0.07
     통합
    -0.07
     runs
    -0.07
     juni
    -0.07
     blacklist
    -0.07
    POSITIVE LOGITS
     потреб
    0.11
     треб
    0.06
     Props
    0.06
     способ
    0.06
     μπο
    0.06
     sposób
    0.06
    AFP
    0.06
     ambassadors
    0.06
    /component
    0.06
    navbarSupportedContent
    0.05
    Act Density 0.003%

    No Known Activations