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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     א
    -0.06
    �
    -0.06
    .Printf
    -0.06
    焦
    -0.06
     lor
    -0.06
    :block
    -0.06
    .YES
    -0.06
     어려
    -0.06
    ::::
    -0.06
    ---
↵
    -0.06
    POSITIVE LOGITS
     yn
    0.07
    ebek
    0.06
    udded
    0.06
     Threshold
    0.06
     feud
    0.06
    confidence
    0.06
    iversit
    0.06
    akat
    0.06
    chang
    0.06
    ูปแบบ
    0.06
    Act Density 0.105%

    No Known Activations