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

    Neuronpedia

    INDEX
    Explanations

    https/http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     copyrights
    -0.08
    Third
    -0.07
    obbies
    -0.06
     tasked
    -0.06
     applicant
    -0.06
     torrent
    -0.06
    DE
    -0.06
    Target
    -0.06
     Monument
    -0.06
    represented
    -0.06
    POSITIVE LOGITS
    nums
    0.07
    mpp
    0.06
     Pir
    0.06
    +F
    0.06
     adip
    0.06
     管
    0.06
    овать
    0.06
     масла
    0.06
    <dim
    0.06
    <U
    0.06
    Act Density 0.003%

    No Known Activations