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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Европ
    -0.07
    owy
    -0.07
    	Il
    -0.07
    eným
    -0.06
    Φ
    -0.06
     OW
    -0.06
     remix
    -0.06
     Covers
    -0.06
    hti
    -0.06
    eth
    -0.06
    POSITIVE LOGITS
     xmlDoc
    0.06
    ,state
    0.06
     sont
    0.06
    _Texture
    0.06
     �
    0.06
    ありがとうござ
    0.06
     드라마
    0.06
    στή
    0.06
    horse
    0.06
     loạt
    0.06
    Act Density 0.004%

    No Known Activations