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

    Neuronpedia

    INDEX
    Explanations

    winning competitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     temp
    -0.06
     suppl
    -0.06
    /tos
    -0.06
    _stats
    -0.06
     Hernandez
    -0.06
    	token
    -0.06
     Beng
    -0.06
    .prefix
    -0.06
    映
    -0.06
    Attack
    -0.05
    POSITIVE LOGITS
    онів
    0.07
     ativ
    0.07
    lası
    0.07
    _case
    0.06
    putc
    0.06
    0.06
    	rd
    0.06
    Uploaded
    0.06
     предус
    0.06
     السعودية
    0.06
    Act Density 0.055%

    No Known Activations