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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     registration
    -0.08
     sj
    -0.07
     genuine
    -0.07
     bathrooms
    -0.07
     validation
    -0.07
    ��
    -0.07
     messaging
    -0.06
    valid
    -0.06
    ]){↵
    -0.06
    &);↵↵
    -0.06
    POSITIVE LOGITS
     searchBar
    0.08
    麦
    0.06
     आक
    0.06
    struments
    0.06
     Grü
    0.06
     прос
    0.06
    atten
    0.06
    .Image
    0.06
     دنی
    0.06
    VertexUvs
    0.05
    Act Density 0.007%

    No Known Activations