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

    Neuronpedia

    INDEX
    Explanations

    decisions, difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    statistics
    -0.07
    XYZ
    -0.06
     Astroph
    -0.06
     planetary
    -0.06
    าถ
    -0.06
     aproxim
    -0.06
     rpt
    -0.06
    利
    -0.06
    Fi
    -0.06
    hots
    -0.06
    POSITIVE LOGITS
    extAlignment
    0.07
    勢
    0.07
     сов
    0.07
     reloadData
    0.07
    Participant
    0.06
    .Fixed
    0.06
    igram
    0.06
    urrency
    0.06
    анк
    0.06
     "")
    0.06
    Act Density 0.240%

    No Known Activations