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

    Neuronpedia

    INDEX
    Explanations

    Code/console output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     USS
    -0.06
    	set
    -0.06
    _AND
    -0.06
    shapes
    -0.06
    inema
    -0.06
     kenn
    -0.06
    /Edit
    -0.06
     đức
    -0.06
     台
    -0.06
     osobní
    -0.05
    POSITIVE LOGITS
     vents
    0.08
    違い
    0.07
    글상위
    0.07
    φι
    0.07
     Berlin
    0.07
    OVE
    0.07
    =size
    0.06
    收益
    0.06
     mimetype
    0.06
     ред
    0.06
    Act Density 0.012%

    No Known Activations