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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bleach
    -0.07
     conceived
    -0.07
     deceive
    -0.07
     Museum
    -0.06
     清
    -0.06
    女子
    -0.06
     understand
    -0.06
     Hut
    -0.06
    FU
    -0.06
     claimed
    -0.06
    POSITIVE LOGITS
     Newly
    0.07
    /static
    0.07
     Tutor
    0.06
    _only
    0.06
    @property
    0.06
     *((
    0.06
     när
    0.06
     Wenn
    0.06
     �
    0.06
     SPDX
    0.06
    Act Density 0.027%

    No Known Activations