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

    Neuronpedia

    INDEX
    Explanations

    lab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NDER
    -0.07
     Glover
    -0.07
    沒
    -0.07
    ues
    -0.07
     gest
    -0.06
     ck
    -0.06
    媽媽
    -0.06
     targetType
    -0.06
    口中
    -0.06
     intrigue
    -0.06
    POSITIVE LOGITS
    landing
    0.07
    form
    0.07
     thread
    0.07
     claimed
    0.07
    ーム
    0.07
    掌控
    0.07
    过往
    0.07
     Rogue
    0.07
     raising
    0.07
     stacked
    0.07
    Act Density 0.001%

    No Known Activations