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

    Neuronpedia

    INDEX
    Explanations

    professional networking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offensive
    -0.07
     objc
    -0.07
    agini
    -0.07
     provided
    -0.07
    Programming
    -0.07
    analytics
    -0.06
     dial
    -0.06
     NT
    -0.06
    edeyse
    -0.06
     declared
    -0.06
    POSITIVE LOGITS
     Fakült
    0.06
     har
    0.06
    _depend
    0.06
     fantastic
    0.06
    Century
    0.06
    าผ
    0.06
    Ế
    0.06
    СО
    0.06
     BIO
    0.06
    .constants
    0.05
    Act Density 0.077%

    No Known Activations