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

    Neuronpedia

    INDEX
    Explanations

    Commons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inspiration
    -0.09
    priced
    -0.08
     imagined
    -0.08
     qiym
    -0.08
     Dungeon
    -0.08
     nostalgic
    -0.08
     admired
    -0.08
     idiyele
    -0.08
     anticipation
    -0.08
     aprovech
    -0.08
    POSITIVE LOGITS
     physician
    0.08
     pharmacist
    0.08
     Leder
    0.08
     clinicians
    0.08
    異
    0.07
     σα
    0.07
     physicians
    0.07
     trast
    0.07
     ≥
    0.07
    α
    0.07
    Act Density 0.004%

    No Known Activations