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

    Neuronpedia

    INDEX
    Explanations

    Data science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touching
    -0.07
    artisan
    -0.07
    awning
    -0.07
     dawn
    -0.06
     Distribution
    -0.06
     AFP
    -0.06
     plain
    -0.06
     arrows
    -0.06
     walkers
    -0.06
     ноч
    -0.06
    POSITIVE LOGITS
     непосред
    0.06
     Args
    0.06
     рань
    0.06
    "]=>
    0.06
    <TResult
    0.06
    SHOP
    0.06
    NM
    0.06
     nv
    0.06
    >";
↵
    0.06
    Pose
    0.06
    Act Density 0.081%

    No Known Activations