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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anch
    -0.07
    lectric
    -0.06
    Map
    -0.06
    corp
    -0.06
     comport
    -0.06
     indicted
    -0.06
     Veronica
    -0.06
    Stock
    -0.06
     THEIR
    -0.06
    cac
    -0.06
    POSITIVE LOGITS
     reprint
    0.07
     Ск
    0.07
     negotiating
    0.06
     extensive
    0.06
     вв
    0.06
    mentions
    0.06
    .calc
    0.06
     sama
    0.06
    arms
    0.06
     coworkers
    0.06
    Act Density 0.147%

    No Known Activations