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

    Neuronpedia

    INDEX
    Explanations

    code and regex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ุล
    -0.07
    ]},
    -0.07
    sqrt
    -0.07
    	Camera
    -0.07
     echo
    -0.07
    .any
    -0.06
     drift
    -0.06
    >(),
    -0.06
    brates
    -0.06
    ouncy
    -0.06
    POSITIVE LOGITS
    ナル
    0.07
    タイ
    0.06
    zano
    0.06
    月
    0.06
    เน
    0.06
     كور
    0.06
    _cust
    0.06
     escre
    0.06
     expanding
    0.06
    ":"","
    0.06
    Act Density 0.017%

    No Known Activations