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

    Neuronpedia

    INDEX
    Explanations

    Phoenix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    curr
    -0.08
     staple
    -0.07
     takes
    -0.07
    LR
    -0.06
     쪽
    -0.06
    .av
    -0.06
    SUB
    -0.06
     irre
    -0.06
    					↵
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Phoenix
    0.20
    Phoenix
    0.17
     phoenix
    0.13
    oenix
    0.11
     Genesis
    0.08
    Genesis
    0.08
     poisonous
    0.08
     setBackgroundColor
    0.08
     Providence
    0.07
     ServiceException
    0.07
    Act Density 0.002%

    No Known Activations