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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Herc
    -0.07
     hoops
    -0.07
     bere
    -0.07
     GROUP
    -0.06
     sets
    -0.06
     LPARAM
    -0.06
     Quart
    -0.06
     Suzuki
    -0.06
     mænd
    -0.06
    Matt
    -0.06
    POSITIVE LOGITS
     зем
    0.07
    ilmesi
    0.07
     sean
    0.07
    .assertIsNot
    0.06
    Optional
    0.06
    (">
    0.06
     Option
    0.06
    respuesta
    0.06
    /dev
    0.06
    reveal
    0.06
    Act Density 0.000%

    No Known Activations