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

    Neuronpedia

    INDEX
    Explanations

    states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ihanna
    -0.08
    Š
    -0.07
    ߡ
    -0.07
    奔
    -0.07
     sleeve
    -0.07
    ве
    -0.07
    릿
    -0.07
    摸
    -0.06
     herself
    -0.06
     bụng
    -0.06
    POSITIVE LOGITS
     URI
    0.08
     situated
    0.07
    observer
    0.07
     Decision
    0.07
    诊疗
    0.07
    logic
    0.07
     unfavorable
    0.07
    .repositories
    0.07
    .RichTextBox
    0.07
    .factory
    0.07
    Act Density 0.033%

    No Known Activations