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

    Neuronpedia

    INDEX
    Explanations

    pop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    👦
    -0.08
    讧
    -0.07
    앱
    -0.07
    劲
    -0.07
    ень
    -0.07
    orum
    -0.07
    ינטרנט
    -0.07
     earns
    -0.07
     Racing
    -0.07
    /menu
    -0.07
    POSITIVE LOGITS
    .Diagnostics
    0.07
     restrained
    0.07
     viper
    0.07
    alling
    0.07
    HTTPHeader
    0.07
    �
    0.07
    .datab
    0.06
    acionales
    0.06
     wire
    0.06
    :@
    0.06
    Act Density 0.003%

    No Known Activations