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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reactionary
    -0.07
    适
    -0.07
    orpor
    -0.06
    _STATUS
    -0.06
    asyarakat
    -0.06
     mam
    -0.06
     JWT
    -0.06
     Coffee
    -0.06
    amphetamine
    -0.06
     情
    -0.06
    POSITIVE LOGITS
    ynchron
    0.07
    <Transform
    0.07
    abay
    0.07
    .textColor
    0.07
     COLL
    0.06
    (snapshot
    0.06
    .Safe
    0.06
    諸
    0.06
     Grave
    0.06
    validators
    0.06
    Act Density 0.011%

    No Known Activations