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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     articulate
    -0.08
     felt
    -0.07
     timelines
    -0.07
     Mart
    -0.07
     Acceler
    -0.06
    치를
    -0.06
    ylabel
    -0.06
     Houses
    -0.06
     houses
    -0.06
     slide
    -0.06
    POSITIVE LOGITS
    航
    0.06
     रक
    0.06
    FACT
    0.06
    utf
    0.06
    _single
    0.06
    ΙΤ
    0.06
    ूष
    0.05
     rifles
    0.05
     nimi
    0.05
    Returning
    0.05
    Act Density 0.007%

    No Known Activations