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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     不
    -0.07
     Father
    -0.07
    เฉล
    -0.07
     father
    -0.07
     �
    -0.07
    熊
    -0.06
     Never
    -0.06
     مكان
    -0.06
     swamp
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ({↵
    0.07
    '}↵↵
    0.06
    .getEntity
    0.06
    	jQuery
    0.06
    startIndex
    0.06
    prung
    0.06
    爱
    0.06
    victim
    0.06
    _IDS
    0.06
     ACK
    0.06
    Act Density 0.202%

    No Known Activations