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
     Kirk
    -0.07
     nhóm
    -0.06
     Algebra
    -0.06
     ganze
    -0.06
     connected
    -0.06
    filme
    -0.06
    内部
    -0.06
     Process
    -0.06
    NET
    -0.06
    	Intent
    -0.06
    POSITIVE LOGITS
     사용
    0.07
    ousing
    0.07
    _guide
    0.06
    isOk
    0.06
    楼
    0.06
    annis
    0.06
    �
    0.06
    gli
    0.06
    ースト
    0.06
    .singletonList
    0.06
    Act Density 0.012%

    No Known Activations