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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     address
    -0.07
     interface
    -0.07
     short
    -0.07
    ()>
    -0.06
    undai
    -0.06
     Benny
    -0.06
     demos
    -0.06
     Monster
    -0.06
     podcast
    -0.06
    ω
    -0.06
    POSITIVE LOGITS
    am
    0.11
    Amount
    0.08
     çocuğ
    0.08
    dam
    0.08
    m
    0.07
    ham
    0.07
    olem
    0.07
    nom
    0.07
    ам
    0.07
     fully
    0.07
    Act Density 0.072%

    No Known Activations