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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     origins
    -0.06
    .af
    -0.06
     chang
    -0.06
     clases
    -0.06
    foto
    -0.06
    われ
    -0.06
     Rita
    -0.06
    oun
    -0.06
    받
    -0.06
     habitual
    -0.06
    POSITIVE LOGITS
    sil
    0.06
     ListViewItem
    0.06
    <Data
    0.06
     Sync
    0.06
     compatible
    0.06
     rebuilt
    0.06
    743
    0.06
    .Network
    0.06
    …it
    0.06
    íše
    0.06
    Act Density 0.048%

    No Known Activations