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

    Neuronpedia

    INDEX
    Explanations

    future tense/hypothetical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -tags
    -0.07
    جات
    -0.06
    affiliate
    -0.06
    spb
    -0.06
    �
    -0.06
    ánu
    -0.06
    麦
    -0.06
    ソン
    -0.06
     поскольку
    -0.06
    ád
    -0.06
    POSITIVE LOGITS
     電
    0.07
     INSTANCE
    0.07
    Ｅ
    0.06
     contour
    0.06
    intel
    0.06
     привод
    0.06
     ileri
    0.06
    手机
    0.06
    Ctx
    0.06
    _dense
    0.06
    Act Density 0.060%

    No Known Activations