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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    副
    -0.07
    .savefig
    -0.07
    阿
    -0.07
    .openg
    -0.07
     handset
    -0.06
    AccessorType
    -0.06
     موارد
    -0.06
    leaflet
    -0.06
     kam
    -0.06
     Flo
    -0.06
    POSITIVE LOGITS
    огу
    0.07
    liable
    0.06
    enaries
    0.06
     fiscal
    0.06
     contamin
    0.06
    ІІ
    0.06
    orous
    0.06
    initely
    0.06
     ию
    0.06
    pizza
    0.06
    Act Density 0.063%

    No Known Activations