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

    Neuronpedia

    INDEX
    Explanations

    being alone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .focus
    -0.06
    .qu
    -0.06
     testimon
    -0.06
    ordin
    -0.06
    tps
    -0.06
     stronghold
    -0.06
     นาย
    -0.06
     disposit
    -0.06
    :t
    -0.06
     dein
    -0.06
    POSITIVE LOGITS
    unts
    0.07
    тися
    0.07
    oster
    0.07
     Bing
    0.07
    trag
    0.07
    iao
    0.07
     Point
    0.07
     folder
    0.07
    annya
    0.06
     CTRL
    0.06
    Act Density 0.000%

    No Known Activations