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

    Neuronpedia

    INDEX
    Explanations

    code/program options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drink
    -0.07
    .Element
    -0.06
    BuilderFactory
    -0.06
    .tp
    -0.06
     HDF
    -0.06
    (Return
    -0.06
    iffs
    -0.06
    Lazy
    -0.06
     obey
    -0.06
    paginate
    -0.06
    POSITIVE LOGITS
     regress
    0.07
    ogens
    0.06
    	ll
    0.06
     зі
    0.06
     갤
    0.06
    _A
    0.06
    ilit
    0.06
    ایش
    0.06
     stint
    0.06
    _NODE
    0.06
    Act Density 0.066%

    No Known Activations