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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CONTENT
    -0.08
     Crime
    -0.07
    overnment
    -0.07
    interpret
    -0.07
    okers
    -0.07
     impres
    -0.07
    禁区
    -0.07
    peated
    -0.07
    PRESENT
    -0.07
     apoptosis
    -0.07
    POSITIVE LOGITS
    	startActivity
    0.08
    ];
↵
↵
    0.08
    }
↵
↵
↵
    0.08
    }
↵
↵
↵
↵
    0.08
    lop
    0.07
     '/');↵
    0.07
     إن
    0.07
    **/↵↵
    0.07
    */↵↵↵
    0.07
    ）。
    0.07
    Act Density 0.348%

    No Known Activations