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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Negative
    -0.07
     emissions
    -0.06
    ="'+
    -0.06
     Merge
    -0.06
     Items
    -0.06
     replicated
    -0.06
    _prog
    -0.06
     Imp
    -0.06
     -*-↵
    -0.06
    โรง
    -0.06
    POSITIVE LOGITS
    Twitter
    0.07
    ète
    0.07
     бл
    0.06
    Cream
    0.06
    �
    0.06
    opro
    0.06
    _INPUT
    0.06
     Registr
    0.06
     Dr
    0.06
     gy
    0.06
    Act Density 0.012%

    No Known Activations