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

    Neuronpedia

    INDEX
    Explanations

    stri

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     momentum
    -0.07
    .Dependency
    -0.06
    Hub
    -0.06
    acent
    -0.06
    уч
    -0.06
     maintain
    -0.06
    енко
    -0.06
     مذ
    -0.06
    CAL
    -0.06
    Capabilities
    -0.06
    POSITIVE LOGITS
     stri
    0.14
    ريط
    0.07
     Horny
    0.07
    umbotron
    0.06
    itary
    0.06
    してる
    0.06
     Spiele
    0.06
     �
    0.06
    "]);↵
    0.06
    ){
↵
    0.06
    Act Density 0.001%

    No Known Activations