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

    Neuronpedia

    INDEX
    Explanations

    travel stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .direct
    -0.06
     �
    -0.06
     grids
    -0.06
    合
    -0.06
     REFER
    -0.06
     greens
    -0.06
     То
    -0.06
     hats
    -0.06
    貨
    -0.06
     Та
    -0.05
    POSITIVE LOGITS
     huis
    0.07
     Experiment
    0.06
    rios
    0.06
     Quint
    0.06
    िछल
    0.06
     Exit
    0.06
     loadImage
    0.06
     Bonus
    0.06
     Grammar
    0.06
     отд
    0.06
    Act Density 0.099%

    No Known Activations