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

    Neuronpedia

    INDEX
    Explanations

    Facebook

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Below
    -0.07
     });↵↵↵↵
    -0.07
     schle
    -0.06
    rolling
    -0.06
    predicate
    -0.06
     Optimization
    -0.06
    _clause
    -0.06
     panic
    -0.06
    inement
    -0.06
     hanno
    -0.06
    POSITIVE LOGITS
     disrupted
    0.06
     dues
    0.06
     pq
    0.06
    (numpy
    0.06
    OTTOM
    0.06
     recipes
    0.06
     koc
    0.06
    dni
    0.06
    เช
    0.06
    escort
    0.06
    Act Density 0.007%

    No Known Activations