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

    Neuronpedia

    INDEX
    Explanations

    ator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    Ross
    -0.07
    好
    -0.07
     economies
    -0.07
     Fah
    -0.07
    chef
    -0.06
    .Year
    -0.06
     bene
    -0.06
    萬
    -0.06
    并
    -0.06
    POSITIVE LOGITS
     Tibet
    0.17
    igator
    0.11
    igators
    0.09
    ator
    0.08
    irth
    0.07
    Trigger
    0.07
     Birch
    0.07
     backButton
    0.06
    xit
    0.06
    metis
    0.06
    Act Density 0.002%

    No Known Activations