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

    Neuronpedia

    INDEX
    Explanations

    catchy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seller
    -0.07
     NUITKA
    -0.07
    uitka
    -0.07
     consulted
    -0.07
    ملكة
    -0.06
    ,title
    -0.06
    stin
    -0.06
    학생
    -0.06
     replacing
    -0.06
     Mapping
    -0.06
    POSITIVE LOGITS
     gerade
    0.07
    ِل
    0.06
    -song
    0.06
    olution
    0.06
    .HORIZONTAL
    0.06
    izzer
    0.06
     Guru
    0.06
     Aer
    0.06
    461
    0.06
    ِر
    0.06
    Act Density 0.057%

    No Known Activations