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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _I
    -0.07
     terminating
    -0.07
    exampleInputEmail
    -0.06
     bilateral
    -0.06
    umar
    -0.06
    occo
    -0.06
    @",
    -0.06
    ');</
    -0.06
     undisclosed
    -0.06
     ][
    -0.06
    POSITIVE LOGITS
     adultos
    0.07
    خراج
    0.07
     bás
    0.07
    Ο�
    0.06
     prive
    0.06
     Soviet
    0.06
    unate
    0.06
    Worksheet
    0.06
    FULL
    0.06
    　　 　 　
    0.06
    Act Density 0.096%

    No Known Activations