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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boxed
    -0.07
     semaphore
    -0.07
    	tr
    -0.06
     sinc
    -0.06
     до
    -0.06
    　　　　　 　
    -0.06
     inward
    -0.06
     helmets
    -0.06
    ();↵↵↵↵
    -0.06
    "..
    -0.06
    POSITIVE LOGITS
    τύ
    0.07
    -direct
    0.07
     Justice
    0.06
    ledged
    0.06
    .await
    0.06
     inhab
    0.06
     ύ
    0.06
    ്�
    0.06
     parish
    0.06
    Holy
    0.06
    Act Density 0.008%

    No Known Activations