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

    Neuronpedia

    INDEX
    Explanations

    academic text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    codegen
    -0.07
     pues
    -0.06
     виник
    -0.06
     варі
    -0.06
    -sponsored
    -0.06
     neck
    -0.05
     خم
    -0.05
    _address
    -0.05
     seja
    -0.05
     콜
    -0.05
    POSITIVE LOGITS
    orget
    0.07
     роботи
    0.07
    함
    0.07
     darn
    0.07
     무
    0.07
     gez
    0.06
    usahaan
    0.06
     कप
    0.06
     Hra
    0.06
    opup
    0.06
    Act Density 0.072%

    No Known Activations