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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     className
    -0.07
     Centers
    -0.07
    (py
    -0.07
     reproductive
    -0.06
     risks
    -0.06
     banyak
    -0.06
    <h
    -0.06
    ñas
    -0.06
    leur
    -0.06
    ffffff
    -0.06
    POSITIVE LOGITS
    rowning
    0.06
     rankings
    0.06
    IntoConstraints
    0.06
     활용
    0.06
    0.06
    ければ
    0.06
    Ngoài
    0.06
     coworkers
    0.06
     Chow
    0.06
     미
    0.06
    Act Density 0.016%

    No Known Activations