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

    Neuronpedia

    INDEX
    Explanations

    conversational

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    싱
    -0.08
    __)
    -0.07
     بها
    -0.07
    ധ
    -0.07
     становится
    -0.07
     border
    -0.07
     advertisement
    -0.07
    oggle
    -0.07
    plet
    -0.06
    )\↵
    -0.06
    POSITIVE LOGITS
    _ax
    0.07
    _GUI
    0.07
     Fleet
    0.07
    Parts
    0.07
    FOX
    0.07
    Property
    0.07
    strategy
    0.07
     Gravity
    0.07
    legalArgumentException
    0.07
     Dick
    0.07
    Act Density 0.208%

    No Known Activations