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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     λα
    -0.06
    imulation
    -0.06
    urator
    -0.06
     rooftop
    -0.06
     Package
    -0.06
    shown
    -0.06
    idual
    -0.06
    ρας
    -0.06
     Colum
    -0.06
     cele
    -0.06
    POSITIVE LOGITS
    <Task
    0.07
     disrespect
    0.06
     explodes
    0.06
     وقد
    0.06
    ItemAt
    0.06
    :Boolean
    0.06
     reserves
    0.06
    (encoded
    0.06
    (parse
    0.06
    pedo
    0.06
    Act Density 0.166%

    No Known Activations