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

    Neuronpedia

    INDEX
    Explanations

    }{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arding
    -0.07
     Valk
    -0.06
     snow
    -0.06
     unicorn
    -0.06
    icians
    -0.06
     collider
    -0.06
    BuildContext
    -0.06
     sentimental
    -0.06
    uro
    -0.06
    "description
    -0.06
    POSITIVE LOGITS
    _TEM
    0.07
     ăn
    0.07
    곡
    0.07
     Quotes
    0.07
    ?>/
    0.06
    _MAT
    0.06
    tery
    0.06
     arous
    0.06
    ackets
    0.06
    风
    0.06
    Act Density 0.046%

    No Known Activations