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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inmates
    -0.07
    ipp
    -0.07
    placeholders
    -0.07
     <=
    -0.06
    jections
    -0.06
     Patent
    -0.06
     violence
    -0.06
     ∈
    -0.06
    Util
    -0.06
    ()">↵
    -0.06
    POSITIVE LOGITS
    för
    0.06
     jewels
    0.06
     humiliation
    0.06
    /man
    0.06
     siempre
    0.06
    -can
    0.06
    .jasper
    0.06
     막
    0.06
    들을
    0.06
     mẹ
    0.05
    Act Density 0.022%

    No Known Activations