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

    Neuronpedia

    INDEX
    Explanations

    director

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jihad
    -0.07
    >Your
    -0.07
    美國
    -0.06
    寒
    -0.06
     Gott
    -0.06
     �
    -0.06
     گیاه
    -0.06
    _IT
    -0.06
    EVER
    -0.06
     Shopify
    -0.06
    POSITIVE LOGITS
    нести
    0.07
    .deepEqual
    0.07
     circumstance
    0.07
     Relationships
    0.06
     Played
    0.06
     FileSystem
    0.06
    žil
    0.06
    -controller
    0.06
     Lieutenant
    0.06
        
↵
    0.06
    Act Density 0.002%

    No Known Activations