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

    Neuronpedia

    INDEX
    Explanations

    social media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     force
    -0.07
    يرا
    -0.06
    ่าย
    -0.06
     Titan
    -0.06
    ();

↵
    -0.06
     فار
    -0.06
    antages
    -0.06
     luaL
    -0.06
     лож
    -0.06
     summoned
    -0.06
    POSITIVE LOGITS
    DownList
    0.07
    анны
    0.07
    IMITIVE
    0.07
     nausea
    0.07
     Prosec
    0.06
    holiday
    0.06
     BED
    0.06
     EB
    0.06
    イズ
    0.06
     Geometry
    0.06
    Act Density 0.087%

    No Known Activations