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

    Neuronpedia

    INDEX
    Explanations

    NO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EMON
    -0.07
     fingert
    -0.07
    -in
    -0.07
    标题
    -0.06
    urs
    -0.06
     elimination
    -0.06
     survives
    -0.06
    あった
    -0.06
     Sevent
    -0.06
    회
    -0.06
    POSITIVE LOGITS
     investing
    0.07
     NP
    0.07
    ình
    0.06
     مرکزی
    0.06
    _particles
    0.06
     isbn
    0.06
    (Method
    0.06
     brightly
    0.06
    夏
    0.06
     Alley
    0.06
    Act Density 0.001%

    No Known Activations