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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hex
    -0.07
    י�
    -0.06
    ез
    -0.06
    小时
    -0.06
     bunny
    -0.06
    엘
    -0.06
     Garc
    -0.06
    site
    -0.06
    Minimal
    -0.06
     средств
    -0.06
    POSITIVE LOGITS
    SPACE
    0.07
    assen
    0.07
    utenant
    0.06
    .=
    0.06
    >tag
    0.06
     preference
    0.06
     glazed
    0.06
     sliding
    0.06
     repl
    0.06
     aan
    0.06
    Act Density 0.257%

    No Known Activations