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

    Neuronpedia

    INDEX
    Explanations

    the word "working"

    oai_token-act-pair · gemini-2.0-flash

    working

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hendes
    -0.51
     ibland
    -0.44
     francesa
    -0.44
     samfun
    -0.43
    erencia
    -0.42
     fizeram
    -0.41
     nenhuma
    -0.41
     francus
    -0.41
     särsk
    -0.40
     TestBed
    -0.40
    POSITIVE LOGITS
    AsUp
    0.67
     المعيارى
    0.67
     kasarigan
    0.66
    tvguidetime
    0.66
     Akismet
    0.65
    CGRectMake
    0.64
    日閲覧
    0.64
    AfterClass
    0.63
     endblock
    0.63
    OrBuilder
    0.63
    Act Density 0.262%

    No Known Activations