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

    Neuronpedia

    INDEX
    Explanations

    legislation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neighborhoods
    -0.07
     singled
    -0.07
     deck
    -0.07
     previews
    -0.06
     crypto
    -0.06
     Injection
    -0.06
    Observ
    -0.06
     fsm
    -0.06
     display
    -0.06
     flushing
    -0.06
    POSITIVE LOGITS
    =create
    0.07
    _Abstract
    0.06
    .DataAccess
    0.06
     大阪
    0.06
     이러한
    0.06
     utilise
    0.06
     Iterator
    0.06
    clidean
    0.06
    headed
    0.06
    078
    0.06
    Act Density 0.005%

    No Known Activations