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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (holder
    -0.08
     resourceName
    -0.07
    oron
    -0.07
    _dist
    -0.06
     okhttp
    -0.06
    (""),
    -0.06
     consecutive
    -0.06
    _oct
    -0.06
    _down
    -0.06
     vd
    -0.06
    POSITIVE LOGITS
     Burns
    0.07
     sess
    0.06
    inář
    0.06
    /spec
    0.06
     strawberry
    0.06
    ateway
    0.06
    철
    0.06
    вич
    0.06
     क
    0.06
     Hawkins
    0.06
    Act Density 0.001%

    No Known Activations