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

    Neuronpedia

    INDEX
    Explanations

    relation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    htar
    -0.06
    LS
    -0.06
    EndTime
    -0.06
    .Program
    -0.06
    .course
    -0.06
    flix
    -0.06
     Near
    -0.06
    <byte
    -0.06
     |
    -0.06
    (marker
    -0.06
    POSITIVE LOGITS
    limitations
    0.07
     relations
    0.07
     thuế
    0.06
    estation
    0.06
    ITLE
    0.06
     sn
    0.06
     resetting
    0.06
     Bennett
    0.06
     compt
    0.06
    해야
    0.06
    Act Density 0.015%

    No Known Activations