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

    Neuronpedia

    INDEX
    Explanations

    Instructions to language model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blanket
    -0.09
     ehr
    -0.08
     blankets
    -0.08
     grap
    -0.08
     oks
    -0.08
     sebesar
    -0.08
    (':
    -0.07
     nire
    -0.07
     rango
    -0.07
    ులతో
    -0.07
    POSITIVE LOGITS
     excerpts
    0.08
     indes
    0.08
     romance
    0.08
    Bah
    0.08
     lyric
    0.07
     myth
    0.07
    Basically
    0.07
     đoạn
    0.07
    agment
    0.07
    ecure
    0.07
    Act Density 0.054%

    No Known Activations