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

    Neuronpedia

    INDEX
    Explanations

    Scientific names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /the
    -0.07
     orchestr
    -0.06
    (BuildContext
    -0.06
    Ant
    -0.06
     Sigma
    -0.06
    .Glide
    -0.06
    .GONE
    -0.06
    /oct
    -0.06
     sơn
    -0.06
     встанов
    -0.06
    POSITIVE LOGITS
     songwriter
    0.07
    ัวหน
    0.07
     Engineer
    0.06
    :::::::::::::
    0.06
     strangely
    0.06
     farming
    0.06
     remodel
    0.06
    rad
    0.06
     commits
    0.06
     Familie
    0.06
    Act Density 0.018%

    No Known Activations