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

    Neuronpedia

    INDEX
    Explanations

    code, court rulings, and other legal/mathematical jargon

    oai_token-act-pair · gemini-2.0-flash

    legal and scientific documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saites
    -0.66
    AccessorTable
    -0.65
    IsContent
    -0.64
    󠁢
    -0.63
    (!__
    -0.60
    rawtypes
    -0.56
     relâche
    -0.55
     AssemblyTitle
    -0.54
    öszi
    -0.50
    OGND
    -0.50
    POSITIVE LOGITS
    клопе
    0.75
    ButterKnife
    0.59
     stand
    0.49
     stood
    0.49
    stood
    0.48
     harde
    0.46
     stali
    0.45
    бище
    0.43
     stands
    0.43
     SVD
    0.43
    Act Density 1.276%

    No Known Activations