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

    Neuronpedia

    INDEX
    Explanations

    code related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     июля
    -0.07
     POWER
    -0.07
    量
    -0.07
    養
    -0.07
     Kings
    -0.06
    XA
    -0.06
     якій
    -0.06
     ourselves
    -0.06
    养
    -0.06
     american
    -0.06
    POSITIVE LOGITS
     злоч
    0.07
    .onreadystatechange
    0.06
    CppTypeDefinitionSizes
    0.06
    олж
    0.06
    移動
    0.06
     Cumhurbaşkanı
    0.06
    '];?>"
    0.06
     nouve
    0.06
    .spaceBetween
    0.06
     Beaut
    0.06
    Act Density 0.092%

    No Known Activations