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

    Neuronpedia

    INDEX
    Explanations

    C# namespace declarations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝕦
    -0.08
    疫
    -0.08
    zac
    -0.07
    .resp
    -0.07
    日电
    -0.07
     четыре
    -0.07
    OLLOW
    -0.07
    electric
    -0.07
    YC
    -0.07
    Lights
    -0.06
    POSITIVE LOGITS
    碎片
    0.07
    ']
    0.07
     throughput
    0.07
    と言
    0.07
    .Iterator
    0.07
     profitable
    0.07
    "`↵↵
    0.07
    车队
    0.07
     jobId
    0.06
    ないように
    0.06
    Act Density 0.001%

    No Known Activations