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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AW
    -0.07
     thickness
    -0.07
     retries
    -0.07
     leader
    -0.07
     বাঁ
    -0.07
     organizations
    -0.07
     scaffold
    -0.07
    ấp
    -0.07
    四川
    -0.07
     payload
    -0.07
    POSITIVE LOGITS
    광
    0.08
    Included
    0.08
    Bibli
    0.08
     Goldberg
    0.08
     Kindergarten
    0.08
     joku
    0.08
    ktop
    0.08
    色情
    0.08
    onderzoek
    0.08
     какой
    0.08
    Act Density 0.015%

    No Known Activations