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

    Neuronpedia

    INDEX
    Explanations

    area

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حص
    -0.07
    iciální
    -0.07
    _DETECT
    -0.06
    ................................................................
    -0.06
    Endpoints
    -0.06
     bardzo
    -0.06
    acic
    -0.06
    ANGED
    -0.06
     subnet
    -0.06
    ITT
    -0.06
    POSITIVE LOGITS
     disagreement
    0.06
    ーブル
    0.06
    ابقات
    0.06
    GI
    0.06
     upgrades
    0.06
     warranted
    0.06
     ]
↵
    0.06
    Bag
    0.06
    中に
    0.06
     willing
    0.06
    Act Density 0.008%

    No Known Activations