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

    Neuronpedia

    INDEX
    Explanations

    programming and data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #get
    -0.07
     affairs
    -0.06
     recycl
    -0.06
     Carr
    -0.06
    лач
    -0.06
    itial
    -0.06
     ।↵
    -0.06
    ↵
↵
↵
↵
    -0.06
     Hugh
    -0.06
     Return
    -0.06
    POSITIVE LOGITS
     MOS
    0.07
     dětí
    0.07
    descricao
    0.06
    ωσε
    0.06
     chua
    0.06
     ※
    0.06
     futuristic
    0.06
    (Route
    0.06
    �能
    0.06
    ADVERTISEMENT
    0.06
    Act Density 0.030%

    No Known Activations