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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NPC
    -0.07
    بوك
    -0.07
    egrity
    -0.07
    _udp
    -0.07
    옮
    -0.06
    技术支持
    -0.06
    _chg
    -0.06
    lope
    -0.06
     swamp
    -0.06
    reature
    -0.06
    POSITIVE LOGITS
    ![
    0.08
     ,[
    0.07
    머
    0.07
     같
    0.07
    子女
    0.06
     casc
    0.06
    明确提出
    0.06
    _keys
    0.06
     candid
    0.06
    verage
    0.06
    Act Density 0.201%

    No Known Activations