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

    Neuronpedia

    INDEX
    Explanations

    coding errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inctions
    -0.07
     Pluto
    -0.07
     meshes
    -0.07
     Penn
    -0.07
    ilenames
    -0.07
    ctors
    -0.07
    黯
    -0.07
     SpringApplication
    -0.07
    -leaning
    -0.07
    ])]↵
    -0.07
    POSITIVE LOGITS
     moż
    0.07
     khóa
    0.07
    斯基
    0.06
    raphics
    0.06
    Dom
    0.06
    웢
    0.06
    )",
    0.06
    '}
    0.06
    'url
    0.06
    Works
    0.06
    Act Density 0.033%

    No Known Activations