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

    Neuronpedia

    INDEX
    Explanations

    mixed languages and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fre
    -0.07
     tables
    -0.07
     tamp
    -0.07
     Sharks
    -0.06
    kle
    -0.06
     backstage
    -0.06
    -fix
    -0.06
     fw
    -0.06
     DROP
    -0.06
     blind
    -0.06
    POSITIVE LOGITS
    っ
    0.07
     гри
    0.06
     invaluable
    0.06
    ριος
    0.06
     GameController
    0.06
    анія
    0.06
    Выб
    0.06
    .*
    0.06
    thood
    0.06
     đài
    0.06
    Act Density 0.000%

    No Known Activations