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

    Neuronpedia

    INDEX
    Explanations

    proximity and touch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜞
    -0.08
    �
    -0.07
     States
    -0.07
    翛
    -0.07
     thousand
    -0.07
    🥨
    -0.07
    What
    -0.07
    来
    -0.07
    “What
    -0.07
    .w
    -0.07
    POSITIVE LOGITS
    منت
    0.07
     donating
    0.07
     artworks
    0.07
     Toro
    0.07
     glitch
    0.07
     disclosures
    0.07
     callers
    0.07
    视野
    0.07
     deadlines
    0.07
    芒果
    0.07
    Act Density 0.048%

    No Known Activations