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

    Neuronpedia

    INDEX
    Explanations

    bond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fortunate
    -0.07
     evangel
    -0.07
     flowering
    -0.07
    sylvania
    -0.07
    	RTDBG
    -0.07
    とのこと
    -0.07
     anomal
    -0.07
     improbable
    -0.06
    苉
    -0.06
     proceeding
    -0.06
    POSITIVE LOGITS
    恶劣
    0.07
    큭
    0.07
    structions
    0.07
    Lewis
    0.07
    Beauty
    0.07
     열
    0.07
    প
    0.07
     Outs
    0.07
    Worker
    0.07
    늘
    0.07
    Act Density 0.008%

    No Known Activations