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

    Neuronpedia

    INDEX
    Explanations

    Formal language/technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    當
    -0.07
    。当
    -0.06
     önc
    -0.06
    २०
    -0.06
    NGTH
    -0.06
    ,number
    -0.06
    (lr
    -0.06
     �
    -0.06
    аних
    -0.06
    唱
    -0.06
    POSITIVE LOGITS
     Marshall
    0.08
    	CG
    0.07
    server
    0.07
     Petsc
    0.07
     Subcommittee
    0.07
     Gay
    0.07
    	Key
    0.07
     recv
    0.07
     yogurt
    0.07
    Bad
    0.07
    Act Density 0.000%

    No Known Activations