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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Ram
    -0.07
     Mastercard
    -0.07
     Este
    -0.07
     Ro
    -0.07
     taa
    -0.07
    羽
    -0.07
    おすすめ
    -0.07
     acknowledgment
    -0.07
    オンライン
    -0.07
    POSITIVE LOGITS
    FAST
    0.08
    (strategy
    0.08
    (each
    0.08
     prune
    0.08
     gymnastics
    0.08
    Clip
    0.08
    	close
    0.08
     excepción
    0.07
     назнач
    0.07
     sant
    0.07
    Act Density 0.002%

    No Known Activations