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

    Neuronpedia

    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ands
    -0.27
    ç½Ħ
    -0.26
     compt
    -0.25
    Į¨
    -0.25
     Incoming
    -0.25
    _verbose
    -0.24
    iture
    -0.24
    ernote
    -0.24
    Emer
    -0.24
     points
    -0.23
    POSITIVE LOGITS
    åĽ½éĻħåĮĸ
    0.25
    ãģķãģ¾
    0.25
    æĸĻ
    0.25
    åİŁæĸĻ
    0.24
    åıĪ被
    0.24
    Ñħи
    0.24
    ILI
    0.24
    Life
    0.24
    深深çļĦ
    0.24
    \"",
    0.23
    Act Density 1.802%

    No Known Activations