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

    Neuronpedia

    INDEX
    Explanations

    iscrimination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĩĤ
    -0.27
    oven
    -0.26
    ocal
    -0.26
    fect
    -0.26
     Seeder
    -0.25
    .onCreate
    -0.25
    .jsx
    -0.25
     trá»įng
    -0.25
    hower
    -0.24
     deed
    -0.24
    POSITIVE LOGITS
    çĪĨåĩº
    0.29
    èĬ¸
    0.27
    çıŃ级
    0.26
     marg
    0.25
    -na
    0.25
    èĻļå¼±
    0.25
    ï¼ģï¼ģ↵↵
    0.24
     ray
    0.24
     FAILED
    0.24
     weakest
    0.24
    Act Density 0.003%

    No Known Activations