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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (compact
    -0.07
     Під
    -0.07
     bigot
    -0.07
    agus
    -0.06
     fetched
    -0.06
    	image
    -0.06
     下午
    -0.06
     secular
    -0.06
    ینه
    -0.06
    icia
    -0.06
    POSITIVE LOGITS
    ymm
    0.06
     Когда
    0.06
    Excellent
    0.06
    prep
    0.06
     eternal
    0.06
     Prep
    0.06
    ("/{
    0.06
    ::::/
    0.06
     употреб
    0.06
    不存在
    0.06
    Act Density 0.000%

    No Known Activations