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

    Neuronpedia

    INDEX
    Explanations

    focused

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UPLOAD
    -0.07
    day
    -0.07
     doğal
    -0.06
    ्रमण
    -0.06
    246
    -0.06
    (It
    -0.06
    ﻟ
    -0.06
    бо
    -0.06
     TY
    -0.06
    ến
    -0.06
    POSITIVE LOGITS
     focused
    0.09
     aimed
    0.09
     opposed
    0.07
    quis
    0.07
     nurses
    0.07
     Blitz
    0.06
     gez
    0.06
     Mez
    0.06
     objective
    0.06
    ylko
    0.06
    Act Density 0.015%

    No Known Activations