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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inya
    -0.07
    实现
    -0.07
    还没有
    -0.06
     Criminal
    -0.06
    okay
    -0.06
    .guna
    -0.06
    รวย
    -0.06
    统筹推进
    -0.06
    andom
    -0.06
    ȩ
    -0.06
    POSITIVE LOGITS
    מרה
    0.08
    apters
    0.08
    和睦
    0.08
    trees
    0.08
     Bayer
    0.07
     equiv
    0.07
    	req
    0.07
    QUERY
    0.07
    -reference
    0.07
    .urlopen
    0.07
    Act Density 0.043%

    No Known Activations