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

    Neuronpedia

    INDEX
    Explanations

    various words that can be used to address a reader, such as "this", "yes", or "necessary"

    oai_token-act-pair · gemini-2.0-flash

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endphp
    -0.46
     án
    -0.45
    rere
    -0.44
     xperia
    -0.44
     exact
    -0.44
     Kooper
    -0.42
    nambuco
    -0.42
    illons
    -0.42
    וכ
    -0.42
    ubu
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.80
     للاسماء
    0.59
    setViewportView
    0.49
     الحره
    0.49
    ViewFeatures
    0.49
    jsonwebtoken
    0.49
    eltzer
    0.49
     initComponents
    0.48
    enterOuterAlt
    0.48
     StringTokenizer
    0.48
    Act Density 0.460%

    No Known Activations