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

    Neuronpedia

    INDEX
    Explanations

    firebase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =''
    -0.07
    gold
    -0.07
     intact
    -0.07
     Manual
    -0.07
     만
    -0.07
    還是
    -0.07
    NotAllowed
    -0.07
     jj
    -0.07
    vil
    -0.07
     Reform
    -0.06
    POSITIVE LOGITS
    ariate
    0.07
    ℘
    0.07
     careg
    0.07
     inauguration
    0.07
    �
    0.07
     Locations
    0.07
    徘
    0.07
     niezbędn
    0.07
    _recipe
    0.06
    蓊
    0.06
    Act Density 0.001%

    No Known Activations