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

    Neuronpedia

    INDEX
    Explanations

    entry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expect
    -0.06
    _patterns
    -0.06
    �
    -0.06
    、お
    -0.06
    ована
    -0.06
     bekom
    -0.06
     Kaplan
    -0.06
    (_)
    -0.06
     panor
    -0.06
    _EOF
    -0.06
    POSITIVE LOGITS
    ивают
    0.07
     utiliser
    0.06
     utilizar
    0.06
    оград
    0.06
     whatever
    0.06
    Declaration
    0.06
    random
    0.06
    stant
    0.06
     refugees
    0.06
    qli
    0.06
    Act Density 0.000%

    No Known Activations