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

    Neuronpedia

    INDEX
    Explanations

    Rugby

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reasonable
    -0.07
     Valentine
    -0.07
     frantic
    -0.06
     Kaplan
    -0.06
     buurt
    -0.06
     Tumblr
    -0.06
    +(\
    -0.06
     Getter
    -0.06
    	UPROPERTY
    -0.06
     usado
    -0.06
    POSITIVE LOGITS
     ，
    0.06
    _four
    0.06
     elem
    0.06
    .deg
    0.06
    AllWindows
    0.06
    LER
    0.06
     functionalities
    0.06
    功能
    0.06
     forks
    0.06
     zemí
    0.06
    Act Density 0.012%

    No Known Activations