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

    Neuronpedia

    INDEX
    Explanations

    sensitive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    בנייה
    -0.07
     Sadly
    -0.07
    .CodeAnalysis
    -0.07
    RuleContext
    -0.07
    stories
    -0.07
     Deadpool
    -0.07
    选取
    -0.07
     ту
    -0.07
     einer
    -0.06
     typeName
    -0.06
    POSITIVE LOGITS
    高位
    0.08
    yi
    0.07
    .out
    0.07
    ضيف
    0.07
    志
    0.07
    comment
    0.07
    忧
    0.07
    OUCH
    0.07
    STATE
    0.07
    ension
    0.07
    Act Density 0.022%

    No Known Activations