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

    Neuronpedia

    INDEX
    Explanations

    continue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -specific
    -0.08
    ALLENG
    -0.07
    Therefore
    -0.06
     folders
    -0.06
    \Core
    -0.06
    handler
    -0.06
    .Rendering
    -0.06
    ディース
    -0.06
    iciel
    -0.06
     Specific
    -0.06
    POSITIVE LOGITS
     nan
    0.07
     doen
    0.07
    òn
    0.06
    <num
    0.06
    sam
    0.06
     سنت
    0.06
     Estr
    0.06
    rech
    0.06
     Twist
    0.06
     byteArray
    0.06
    Act Density 0.014%

    No Known Activations