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

    Neuronpedia

    INDEX
    Explanations

    mathematical/logical conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ไ
    -0.07
    maa
    -0.07
     milestone
    -0.07
     hunting
    -0.07
     Rama
    -0.07
     decentralized
    -0.07
     milestones
    -0.07
     چه
    -0.07
     מנ
    -0.07
    “
    -0.07
    POSITIVE LOGITS
     被
    0.08
     Polis
    0.08
     préalable
    0.08
     Andes
    0.08
     Hierdoor
    0.07
     Mapping
    0.07
     Navarro
    0.07
     Dishwasher
    0.07
    -facebook
    0.07
     desserts
    0.07
    Act Density 0.051%

    No Known Activations