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

    Neuronpedia

    INDEX
    Explanations

    brackets/quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     될
    -0.06
    pour
    -0.06
     وش
    -0.06
     utiliza
    -0.06
    OMETRY
    -0.06
    >>(↵
    -0.06
    .DEFINE
    -0.06
    .IT
    -0.06
     totaled
    -0.06
    。但
    -0.06
    POSITIVE LOGITS
     GUID
    0.07
    zeň
    0.07
     اصلاح
    0.07
    InView
    0.07
     UIG
    0.07
     Corona
    0.06
     öff
    0.06
     markdown
    0.06
    黑
    0.06
    ۲۵
    0.06
    Act Density 0.001%

    No Known Activations