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

    Neuronpedia

    INDEX
    Explanations

    novel writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecer
    -0.08
    ubuntu
    -0.08
     nto
    -0.08
     Bridge
    -0.07
    .openqa
    -0.07
     đối
    -0.07
     workers
    -0.07
    doğan
    -0.07
    Ngo
    -0.07
     unmanaged
    -0.07
    POSITIVE LOGITS
    =P
    0.08
     sprawling
    0.08
     серия
    0.08
     transcripts
    0.08
    =text
    0.08
    க்க
    0.08
     transcript
    0.08
    详细
    0.08
     detailed
    0.08
     pitching
    0.08
    Act Density 0.056%

    No Known Activations