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

    Neuronpedia

    INDEX
    Explanations

    cancer drug development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    错
    -0.07
    rp
    -0.07
    錯
    -0.06
    Ар
    -0.06
     nursing
    -0.06
     Hell
    -0.06
    _tgt
    -0.06
     
↵ 
↵
    -0.06
    }\
    -0.06
    照
    -0.06
    POSITIVE LOGITS
     Belediyesi
    0.07
    -off
    0.06
    orno
    0.06
    enské
    0.06
    راف
    0.06
    FromFile
    0.06
    ัพย
    0.06
    .scene
    0.06
     드라마
    0.06
    áli
    0.06
    Act Density 0.054%

    No Known Activations