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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adeon
    -0.06
    ですね
    -0.06
    喔
    -0.06
     hele
    -0.06
    を使
    -0.06
     déf
    -0.06
    后
    -0.06
     sadly
    -0.06
    alte
    -0.06
    せて
    -0.06
    POSITIVE LOGITS
     purple
    0.07
    анная
    0.07
     poke
    0.07
     swift
    0.07
     propTypes
    0.07
     bp
    0.06
    iOS
    0.06
     furniture
    0.06
    ंपन
    0.06
    SCRIPTION
    0.06
    Act Density 0.039%

    No Known Activations