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

    Neuronpedia

    INDEX
    Explanations

    social and work life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preferring
    -0.08
    apsed
    -0.07
    (UnityEngine
    -0.07
     brom
    -0.06
    Steel
    -0.06
    Com
    -0.06
     expiry
    -0.06
     BATCH
    -0.06
     Sheep
    -0.06
    ави
    -0.06
    POSITIVE LOGITS
    lerinde
    0.07
     Pete
    0.06
    _der
    0.06
    @if
    0.06
     Ler
    0.06
     Cowboy
    0.06
    ecta
    0.06
     Christine
    0.06
    -wh
    0.06
     AMAZ
    0.06
    Act Density 0.027%

    No Known Activations