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

    Neuronpedia

    INDEX
    Explanations

    recent news, updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     機
    -0.07
    يا
    -0.06
     Either
    -0.06
    voor
    -0.06
    kJ
    -0.06
    熱
    -0.06
    .onDestroy
    -0.06
     Points
    -0.06
     А
    -0.06
     streamlined
    -0.06
    POSITIVE LOGITS
     Peoples
    0.07
     disturbances
    0.06
     createdBy
    0.06
    .setItem
    0.06
    =default
    0.06
    (child
    0.06
     труда
    0.06
    》
    0.06
    抗
    0.06
     dışında
    0.06
    Act Density 0.063%

    No Known Activations