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

    Neuronpedia

    INDEX
    Explanations

    core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _%
    -0.07
     demands
    -0.07
     improvement
    -0.07
     communism
    -0.07
     adapters
    -0.07
    護
    -0.07
    再现
    -0.07
    じゃ
    -0.06
    hf
    -0.06
    timestamps
    -0.06
    POSITIVE LOGITS
     الروسي
    0.07
    宸
    0.07
    .union
    0.07
    proj
    0.07
    .create
    0.07
    -brand
    0.07
    .That
    0.07
     LENG
    0.06
    .Create
    0.06
    正
    0.06
    Act Density 0.005%

    No Known Activations