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

    Neuronpedia

    INDEX
    Explanations

    may/might

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veter
    -0.07
     glad
    -0.07
     Recipes
    -0.07
    .dictionary
    -0.07
    kového
    -0.07
     BCHP
    -0.06
    .ot
    -0.06
     kvinn
    -0.06
     olmak
    -0.06
     hairstyle
    -0.06
    POSITIVE LOGITS
     assaulted
    0.07
    Bộ
    0.06
     pilgr
    0.06
     anti
    0.06
    巡
    0.06
     cams
    0.06
    รส
    0.06
    �能
    0.06
    Longitude
    0.06
    ckett
    0.05
    Act Density 0.019%

    No Known Activations