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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Perry
    -0.07
     Jeremiah
    -0.06
     bonded
    -0.06
    ("'
    -0.06
     Wouldn
    -0.06
    :['
    -0.06
     richness
    -0.06
    春
    -0.06
     facing
    -0.06
     trajectories
    -0.06
    POSITIVE LOGITS
    负
    0.07
     (↵
    0.07
    ：%
    0.07
    arton
    0.07
    OfWork
    0.07
    social
    0.07
    اقع
    0.07
    назнач
    0.07
    soc
    0.07
     TextArea
    0.07
    Act Density 0.003%

    No Known Activations