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

    Neuronpedia

    INDEX
    Explanations

    programming data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stanley
    -0.07
    нам
    -0.07
     CHO
    -0.06
     Dup
    -0.06
     NSObject
    -0.06
     Kami
    -0.06
     فیلم
    -0.06
    "go
    -0.06
     addslashes
    -0.06
     Researchers
    -0.06
    POSITIVE LOGITS
    claim
    0.07
    Chem
    0.06
    .Summary
    0.06
    ğer
    0.06
    uell
    0.06
    ِّ
    0.06
    적인
    0.06
     hük
    0.06
    andidates
    0.06
    lead
    0.06
    Act Density 0.013%

    No Known Activations